Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 14 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9867. Min Range: -3.9867
Max Act: 3.9867. Min Act: -0.1700
Data Index: 5503822 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9867. Min Range: -3.9867
Max Act: 3.9554. Min Act: -0.1700
Data Index: 832293 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9867. Min Range: -3.9867
Max Act: 3.8616. Min Act: -0.1700
Data Index: 5268709 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9867. Min Range: -3.9867
Max Act: 3.8304. Min Act: -0.1700
Data Index: 2349306 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9867. Min Range: -3.9867
Max Act: 3.7991. Min Act: -0.1700
Data Index: 5131802 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9867. Min Range: -3.9867
Max Act: 3.8616. Min Act: -0.1700
Data Index: 102958 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9867. Min Range: -3.9867
Max Act: 3.7991. Min Act: -0.1700
Data Index: 7971354 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9867. Min Range: -3.9867
Max Act: 3.7678. Min Act: -0.1700
Data Index: 3004207 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9867. Min Range: -3.9867
Max Act: 3.7678. Min Act: -0.1700
Data Index: 7150044 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9867. Min Range: -3.9867
Max Act: 3.7678. Min Act: -0.1700
Data Index: 1777157 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9867. Min Range: -3.9867
Max Act: 3.7991. Min Act: -0.1700
Data Index: 8731452 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9867. Min Range: -3.9867
Max Act: 3.7678. Min Act: -0.1700
Data Index: 2677046 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9867. Min Range: -3.9867
Max Act: 3.7365. Min Act: -0.1700
Data Index: 3691568 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9867. Min Range: -3.9867
Max Act: 3.7365. Min Act: -0.1700
Data Index: 3460228 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9867. Min Range: -3.9867
Max Act: 3.7678. Min Act: -0.1700
Data Index: 6938693 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9867. Min Range: -3.9867
Max Act: 3.6740. Min Act: -0.1700
Data Index: 4569530 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9867. Min Range: -3.9867
Max Act: 3.7052. Min Act: -0.1700
Data Index: 3014321 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9867. Min Range: -3.9867
Max Act: 3.7052. Min Act: -0.1700
Data Index: 5477066 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9867. Min Range: -3.9867
Max Act: 3.7052. Min Act: -0.1700
Data Index: 6199105 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9867. Min Range: -3.9867
Max Act: 3.7052. Min Act: -0.1700
Data Index: 6768070 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19