Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4816 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6225. Min Range: -6.6225
Max Act: 6.6225. Min Act: -0.1700
Data Index: 3599390 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6225. Min Range: -6.6225
Max Act: 6.0913. Min Act: -0.1700
Data Index: 6299066 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6225. Min Range: -6.6225
Max Act: 5.9038. Min Act: -0.1700
Data Index: 1966002 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6225. Min Range: -6.6225
Max Act: 5.7788. Min Act: -0.1700
Data Index: 4767418 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6225. Min Range: -6.6225
Max Act: 5.7475. Min Act: -0.1700
Data Index: 2953162 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6225. Min Range: -6.6225
Max Act: 5.7163. Min Act: -0.1700
Data Index: 5043653 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6225. Min Range: -6.6225
Max Act: 5.6850. Min Act: -0.1700
Data Index: 461134 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6225. Min Range: -6.6225
Max Act: 5.6850. Min Act: -0.1700
Data Index: 3737463 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6225. Min Range: -6.6225
Max Act: 5.6850. Min Act: -0.1700
Data Index: 5894969 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6225. Min Range: -6.6225
Max Act: 5.6538. Min Act: -0.1700
Data Index: 1331960 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6225. Min Range: -6.6225
Max Act: 5.6850. Min Act: -0.1700
Data Index: 6685299 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6225. Min Range: -6.6225
Max Act: 5.6850. Min Act: -0.1700
Data Index: 7732701 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6225. Min Range: -6.6225
Max Act: 5.6538. Min Act: -0.1700
Data Index: 3893482 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6225. Min Range: -6.6225
Max Act: 5.6225. Min Act: -0.1700
Data Index: 183006 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6225. Min Range: -6.6225
Max Act: 5.6225. Min Act: -0.1700
Data Index: 4723009 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6225. Min Range: -6.6225
Max Act: 5.5913. Min Act: -0.1700
Data Index: 374682 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6225. Min Range: -6.6225
Max Act: 5.5600. Min Act: -0.1700
Data Index: 4337369 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6225. Min Range: -6.6225
Max Act: 5.5600. Min Act: -0.1700
Data Index: 1686811 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6225. Min Range: -6.6225
Max Act: 5.5600. Min Act: -0.1700
Data Index: 1123193 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6225. Min Range: -6.6225
Max Act: 5.5600. Min Act: -0.1700
Data Index: 8037424 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19