Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1941 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5285. Min Range: -4.5285
Max Act: 4.5285. Min Act: -0.1700
Data Index: 7636434 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5285. Min Range: -4.5285
Max Act: 4.4972. Min Act: -0.1700
Data Index: 2974720 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5285. Min Range: -4.5285
Max Act: 4.4972. Min Act: -0.1700
Data Index: 3050651 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5285. Min Range: -4.5285
Max Act: 4.4972. Min Act: -0.1700
Data Index: 3457079 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5285. Min Range: -4.5285
Max Act: 4.4035. Min Act: -0.1700
Data Index: 2656676 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5285. Min Range: -4.5285
Max Act: 4.3097. Min Act: -0.1700
Data Index: 818195 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5285. Min Range: -4.5285
Max Act: 4.2160. Min Act: -0.1700
Data Index: 1453394 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5285. Min Range: -4.5285
Max Act: 4.2472. Min Act: -0.1700
Data Index: 4803109 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5285. Min Range: -4.5285
Max Act: 4.2472. Min Act: -0.1700
Data Index: 5663920 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5285. Min Range: -4.5285
Max Act: 4.2160. Min Act: -0.1700
Data Index: 4651744 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5285. Min Range: -4.5285
Max Act: 4.2160. Min Act: -0.1700
Data Index: 3137251 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5285. Min Range: -4.5285
Max Act: 4.1847. Min Act: -0.1700
Data Index: 3594909 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5285. Min Range: -4.5285
Max Act: 4.1847. Min Act: -0.1700
Data Index: 3433014 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5285. Min Range: -4.5285
Max Act: 4.1847. Min Act: -0.1700
Data Index: 7373735 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5285. Min Range: -4.5285
Max Act: 4.1535. Min Act: -0.1700
Data Index: 5382711 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5285. Min Range: -4.5285
Max Act: 4.1535. Min Act: -0.1700
Data Index: 3429893 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5285. Min Range: -4.5285
Max Act: 4.1535. Min Act: -0.1700
Data Index: 8189523 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5285. Min Range: -4.5285
Max Act: 4.1535. Min Act: -0.1700
Data Index: 5001392 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5285. Min Range: -4.5285
Max Act: 4.1535. Min Act: -0.1700
Data Index: 6879546 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5285. Min Range: -4.5285
Max Act: 4.1222. Min Act: -0.1700
Data Index: 6225817 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19