Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3737 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0082. Min Range: -4.0082
Max Act: 4.0082. Min Act: -0.1700
Data Index: 3767532 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.9144. Min Act: -0.1700
Data Index: 1829248 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.9144. Min Act: -0.1700
Data Index: 5699175 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.8831. Min Act: -0.1700
Data Index: 2632788 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.8518. Min Act: -0.1700
Data Index: 3855082 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.8362. Min Act: -0.1700
Data Index: 6476859 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.8362. Min Act: -0.1700
Data Index: 8009243 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.8206. Min Act: -0.1700
Data Index: 7334353 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.8206. Min Act: -0.1700
Data Index: 8511098 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.7893. Min Act: -0.1700
Data Index: 4459208 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.7893. Min Act: -0.1700
Data Index: 7232420 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.7424. Min Act: -0.1700
Data Index: 7211443 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.6954. Min Act: -0.1700
Data Index: 4020859 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.7111. Min Act: -0.1700
Data Index: 2118681 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.7267. Min Act: -0.1700
Data Index: 2958346 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.7111. Min Act: -0.1700
Data Index: 3301598 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.6798. Min Act: -0.1700
Data Index: 4548456 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.6954. Min Act: -0.1700
Data Index: 2900324 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.6642. Min Act: -0.1700
Data Index: 6795963 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0082. Min Range: -4.0082
Max Act: 3.6798. Min Act: -0.1700
Data Index: 3104172 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19