Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3351 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3116. Min Range: -8.3116
Max Act: 8.3116. Min Act: -0.1700
Data Index: 320596 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3116. Min Range: -8.3116
Max Act: 7.9366. Min Act: -0.1700
Data Index: 7953691 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3116. Min Range: -8.3116
Max Act: 7.9366. Min Act: -0.1700
Data Index: 6184929 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3116. Min Range: -8.3116
Max Act: 7.8741. Min Act: -0.1700
Data Index: 8172252 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3116. Min Range: -8.3116
Max Act: 7.8116. Min Act: -0.1700
Data Index: 6866745 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3116. Min Range: -8.3116
Max Act: 7.8116. Min Act: -0.1700
Data Index: 6765362 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3116. Min Range: -8.3116
Max Act: 7.6866. Min Act: -0.1700
Data Index: 4088641 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3116. Min Range: -8.3116
Max Act: 7.6866. Min Act: -0.1700
Data Index: 6601429 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3116. Min Range: -8.3116
Max Act: 7.6866. Min Act: -0.1700
Data Index: 6071821 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3116. Min Range: -8.3116
Max Act: 7.6866. Min Act: -0.1700
Data Index: 2847951 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3116. Min Range: -8.3116
Max Act: 7.6866. Min Act: -0.1700
Data Index: 4085159 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3116. Min Range: -8.3116
Max Act: 7.6241. Min Act: -0.1700
Data Index: 2793924 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3116. Min Range: -8.3116
Max Act: 7.5616. Min Act: -0.1700
Data Index: 8155103 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3116. Min Range: -8.3116
Max Act: 7.5616. Min Act: -0.1700
Data Index: 2391097 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3116. Min Range: -8.3116
Max Act: 7.5616. Min Act: -0.1700
Data Index: 8095937 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3116. Min Range: -8.3116
Max Act: 7.5616. Min Act: -0.1700
Data Index: 7959763 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3116. Min Range: -8.3116
Max Act: 7.6241. Min Act: -0.1700
Data Index: 7822551 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3116. Min Range: -8.3116
Max Act: 7.5616. Min Act: -0.1700
Data Index: 5650971 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3116. Min Range: -8.3116
Max Act: 7.5304. Min Act: -0.1700
Data Index: 5770871 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3116. Min Range: -8.3116
Max Act: 7.5304. Min Act: -0.1700
Data Index: 5743320 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #19