Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2530 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8791. Min Range: -6.8791
Max Act: 6.8791. Min Act: -0.1700
Data Index: 619487 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8791. Min Range: -6.8791
Max Act: 6.7853. Min Act: -0.1700
Data Index: 511266 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8791. Min Range: -6.8791
Max Act: 6.6603. Min Act: -0.1700
Data Index: 3839619 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8791. Min Range: -6.8791
Max Act: 6.6291. Min Act: -0.1700
Data Index: 7766436 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8791. Min Range: -6.8791
Max Act: 6.5353. Min Act: -0.1700
Data Index: 2530894 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8791. Min Range: -6.8791
Max Act: 6.5353. Min Act: -0.1700
Data Index: 6987837 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8791. Min Range: -6.8791
Max Act: 6.5041. Min Act: -0.1700
Data Index: 4230201 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8791. Min Range: -6.8791
Max Act: 6.5041. Min Act: -0.1700
Data Index: 5773075 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8791. Min Range: -6.8791
Max Act: 6.5041. Min Act: -0.1700
Data Index: 6332017 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8791. Min Range: -6.8791
Max Act: 6.4728. Min Act: -0.1700
Data Index: 1421982 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8791. Min Range: -6.8791
Max Act: 6.4728. Min Act: -0.1700
Data Index: 681852 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8791. Min Range: -6.8791
Max Act: 6.4416. Min Act: -0.1700
Data Index: 6285539 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8791. Min Range: -6.8791
Max Act: 6.4416. Min Act: -0.1700
Data Index: 5470772 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8791. Min Range: -6.8791
Max Act: 6.4416. Min Act: -0.1700
Data Index: 3893957 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8791. Min Range: -6.8791
Max Act: 6.4416. Min Act: -0.1700
Data Index: 6057010 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8791. Min Range: -6.8791
Max Act: 6.4416. Min Act: -0.1700
Data Index: 5167299 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8791. Min Range: -6.8791
Max Act: 6.4103. Min Act: -0.1700
Data Index: 7508179 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8791. Min Range: -6.8791
Max Act: 6.4103. Min Act: -0.1700
Data Index: 5303477 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8791. Min Range: -6.8791
Max Act: 6.4103. Min Act: -0.1700
Data Index: 37142 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8791. Min Range: -6.8791
Max Act: 6.3791. Min Act: -0.1700
Data Index: 1694317 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19