Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3004 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2935. Min Range: -7.2935
Max Act: 7.2935. Min Act: -0.1700
Data Index: 7588537 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2935. Min Range: -7.2935
Max Act: 7.2622. Min Act: -0.1700
Data Index: 2915554 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2935. Min Range: -7.2935
Max Act: 7.1372. Min Act: -0.1700
Data Index: 5818917 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2935. Min Range: -7.2935
Max Act: 7.0747. Min Act: -0.1700
Data Index: 6399813 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2935. Min Range: -7.2935
Max Act: 7.0435. Min Act: -0.1700
Data Index: 2680029 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2935. Min Range: -7.2935
Max Act: 6.9185. Min Act: -0.1700
Data Index: 8237744 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2935. Min Range: -7.2935
Max Act: 6.9185. Min Act: -0.1700
Data Index: 7999499 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2935. Min Range: -7.2935
Max Act: 6.9185. Min Act: -0.1700
Data Index: 2741430 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2935. Min Range: -7.2935
Max Act: 6.9185. Min Act: -0.1700
Data Index: 5958769 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2935. Min Range: -7.2935
Max Act: 6.8872. Min Act: -0.1700
Data Index: 5475718 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2935. Min Range: -7.2935
Max Act: 6.8560. Min Act: -0.1700
Data Index: 4737836 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2935. Min Range: -7.2935
Max Act: 6.8247. Min Act: -0.1700
Data Index: 5579325 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2935. Min Range: -7.2935
Max Act: 6.8247. Min Act: -0.1700
Data Index: 96076 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2935. Min Range: -7.2935
Max Act: 6.7935. Min Act: -0.1700
Data Index: 2432781 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2935. Min Range: -7.2935
Max Act: 6.7935. Min Act: -0.1700
Data Index: 6457749 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2935. Min Range: -7.2935
Max Act: 6.7935. Min Act: -0.1700
Data Index: 7742407 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2935. Min Range: -7.2935
Max Act: 6.7935. Min Act: -0.1700
Data Index: 3059808 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2935. Min Range: -7.2935
Max Act: 6.7622. Min Act: -0.1700
Data Index: 3529258 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2935. Min Range: -7.2935
Max Act: 6.7622. Min Act: -0.1700
Data Index: 901668 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2935. Min Range: -7.2935
Max Act: 6.7622. Min Act: -0.1700
Data Index: 5941274 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19