Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4494 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 12.3654. Min Range: -12.3654
Max Act: 12.3654. Min Act: -0.1700
Data Index: 7519012 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.3654. Min Range: -12.3654
Max Act: 12.1779. Min Act: -0.1700
Data Index: 2129365 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.3654. Min Range: -12.3654
Max Act: 11.9904. Min Act: -0.1700
Data Index: 2921032 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.3654. Min Range: -12.3654
Max Act: 11.8654. Min Act: -0.1700
Data Index: 1310458 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.3654. Min Range: -12.3654
Max Act: 11.8654. Min Act: -0.1700
Data Index: 5216121 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.3654. Min Range: -12.3654
Max Act: 11.6779. Min Act: -0.1700
Data Index: 4503738 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.3654. Min Range: -12.3654
Max Act: 11.4904. Min Act: -0.1700
Data Index: 492890 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.3654. Min Range: -12.3654
Max Act: 11.4279. Min Act: -0.1700
Data Index: 8444357 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.3654. Min Range: -12.3654
Max Act: 11.3654. Min Act: -0.1700
Data Index: 6220339 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.3654. Min Range: -12.3654
Max Act: 11.3029. Min Act: -0.1700
Data Index: 3752409 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.3654. Min Range: -12.3654
Max Act: 11.3029. Min Act: -0.1700
Data Index: 2158653 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.3654. Min Range: -12.3654
Max Act: 11.3029. Min Act: -0.1700
Data Index: 8751531 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.3654. Min Range: -12.3654
Max Act: 11.2404. Min Act: -0.1700
Data Index: 8444352 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.3654. Min Range: -12.3654
Max Act: 11.2404. Min Act: -0.1700
Data Index: 960994 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.3654. Min Range: -12.3654
Max Act: 11.1779. Min Act: -0.1700
Data Index: 8444345 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.3654. Min Range: -12.3654
Max Act: 11.1779. Min Act: -0.1700
Data Index: 8036328 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.3654. Min Range: -12.3654
Max Act: 11.1779. Min Act: -0.1700
Data Index: 8444360 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.3654. Min Range: -12.3654
Max Act: 11.1154. Min Act: -0.1700
Data Index: 2312612 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.3654. Min Range: -12.3654
Max Act: 10.9904. Min Act: -0.1700
Data Index: 4144676 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.3654. Min Range: -12.3654
Max Act: 11.0529. Min Act: -0.1700
Data Index: 8444351 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19