Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3790 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.8341. Min Act: -0.1700
Data Index: 7150360 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.7091. Min Act: -0.1700
Data Index: 2512149 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.7091. Min Act: -0.1700
Data Index: 2595905 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.6778. Min Act: -0.1700
Data Index: 330946 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.6778. Min Act: -0.1700
Data Index: 5228799 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.6466. Min Act: -0.1700
Data Index: 3217418 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.6153. Min Act: -0.1700
Data Index: 1351601 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.6153. Min Act: -0.1700
Data Index: 2377359 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.6153. Min Act: -0.1700
Data Index: 1576378 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.6153. Min Act: -0.1700
Data Index: 5399886 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.6153. Min Act: -0.1700
Data Index: 921834 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.5841. Min Act: -0.1700
Data Index: 1453184 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.5528. Min Act: -0.1700
Data Index: 8040935 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.5528. Min Act: -0.1700
Data Index: 3187006 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.5528. Min Act: -0.1700
Data Index: 6566118 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.5528. Min Act: -0.1700
Data Index: 4873184 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.5528. Min Act: -0.1700
Data Index: 2839961 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.5528. Min Act: -0.1700
Data Index: 4425076 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.5216. Min Act: -0.1700
Data Index: 313228 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8341. Min Range: -4.8341
Max Act: 4.5528. Min Act: -0.1700
Data Index: 5616817 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19