Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4376 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9539. Min Range: -4.9539
Max Act: 4.9539. Min Act: -0.1700
Data Index: 4793128 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9539. Min Range: -4.9539
Max Act: 4.9226. Min Act: -0.1700
Data Index: 3561199 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9539. Min Range: -4.9539
Max Act: 4.8601. Min Act: -0.1700
Data Index: 3342894 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9539. Min Range: -4.9539
Max Act: 4.8289. Min Act: -0.1700
Data Index: 4987774 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9539. Min Range: -4.9539
Max Act: 4.7976. Min Act: -0.1700
Data Index: 583301 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9539. Min Range: -4.9539
Max Act: 4.7976. Min Act: -0.1700
Data Index: 2537825 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9539. Min Range: -4.9539
Max Act: 4.7664. Min Act: -0.1700
Data Index: 6010938 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9539. Min Range: -4.9539
Max Act: 4.7664. Min Act: -0.1700
Data Index: 7090711 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9539. Min Range: -4.9539
Max Act: 4.7664. Min Act: -0.1700
Data Index: 3462903 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9539. Min Range: -4.9539
Max Act: 4.7664. Min Act: -0.1700
Data Index: 440188 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9539. Min Range: -4.9539
Max Act: 4.7664. Min Act: -0.1700
Data Index: 76011 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9539. Min Range: -4.9539
Max Act: 4.7039. Min Act: -0.1700
Data Index: 4863223 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9539. Min Range: -4.9539
Max Act: 4.7039. Min Act: -0.1700
Data Index: 2565740 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9539. Min Range: -4.9539
Max Act: 4.7039. Min Act: -0.1700
Data Index: 3936650 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9539. Min Range: -4.9539
Max Act: 4.7039. Min Act: -0.1700
Data Index: 4871141 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9539. Min Range: -4.9539
Max Act: 4.7039. Min Act: -0.1700
Data Index: 3880190 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9539. Min Range: -4.9539
Max Act: 4.6726. Min Act: -0.1700
Data Index: 6052605 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9539. Min Range: -4.9539
Max Act: 4.6414. Min Act: -0.1700
Data Index: 824980 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9539. Min Range: -4.9539
Max Act: 4.6726. Min Act: -0.1700
Data Index: 3027980 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9539. Min Range: -4.9539
Max Act: 4.6414. Min Act: -0.1700
Data Index: 1060476 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19