Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1720 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9955. Min Range: -4.9955
Max Act: 4.9955. Min Act: -0.1700
Data Index: 3148794 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9955. Min Range: -4.9955
Max Act: 4.9330. Min Act: -0.1700
Data Index: 8576971 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9955. Min Range: -4.9955
Max Act: 4.9330. Min Act: -0.1700
Data Index: 6544604 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9955. Min Range: -4.9955
Max Act: 4.9018. Min Act: -0.1700
Data Index: 5307730 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9955. Min Range: -4.9955
Max Act: 4.8705. Min Act: -0.1700
Data Index: 7927726 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9955. Min Range: -4.9955
Max Act: 4.8393. Min Act: -0.1700
Data Index: 4860958 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9955. Min Range: -4.9955
Max Act: 4.8393. Min Act: -0.1700
Data Index: 5993937 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9955. Min Range: -4.9955
Max Act: 4.7768. Min Act: -0.1700
Data Index: 234293 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9955. Min Range: -4.9955
Max Act: 4.7768. Min Act: -0.1700
Data Index: 2275869 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9955. Min Range: -4.9955
Max Act: 4.7768. Min Act: -0.1700
Data Index: 5882686 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9955. Min Range: -4.9955
Max Act: 4.8080. Min Act: -0.1700
Data Index: 4900589 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9955. Min Range: -4.9955
Max Act: 4.7143. Min Act: -0.1700
Data Index: 1018297 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9955. Min Range: -4.9955
Max Act: 4.7143. Min Act: -0.1700
Data Index: 6427906 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9955. Min Range: -4.9955
Max Act: 4.7143. Min Act: -0.1700
Data Index: 2831603 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9955. Min Range: -4.9955
Max Act: 4.6830. Min Act: -0.1700
Data Index: 7212412 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9955. Min Range: -4.9955
Max Act: 4.7143. Min Act: -0.1700
Data Index: 2523288 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9955. Min Range: -4.9955
Max Act: 4.7143. Min Act: -0.1700
Data Index: 2256866 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9955. Min Range: -4.9955
Max Act: 4.7143. Min Act: -0.1700
Data Index: 1073021 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9955. Min Range: -4.9955
Max Act: 4.6830. Min Act: -0.1700
Data Index: 4057835 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9955. Min Range: -4.9955
Max Act: 4.7455. Min Act: -0.1700
Data Index: 2916218 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #19