Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4837 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9228. Min Range: -7.9228
Max Act: 7.9228. Min Act: -0.1700
Data Index: 4402546 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9228. Min Range: -7.9228
Max Act: 7.2666. Min Act: -0.1700
Data Index: 3997405 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9228. Min Range: -7.9228
Max Act: 7.2353. Min Act: -0.1700
Data Index: 1812052 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9228. Min Range: -7.9228
Max Act: 7.2666. Min Act: -0.1700
Data Index: 1545910 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9228. Min Range: -7.9228
Max Act: 7.2353. Min Act: -0.1700
Data Index: 8716208 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9228. Min Range: -7.9228
Max Act: 7.2041. Min Act: -0.1700
Data Index: 5529184 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9228. Min Range: -7.9228
Max Act: 7.2041. Min Act: -0.1700
Data Index: 6759275 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9228. Min Range: -7.9228
Max Act: 7.2041. Min Act: -0.1700
Data Index: 3742583 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9228. Min Range: -7.9228
Max Act: 7.2041. Min Act: -0.1700
Data Index: 5535253 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9228. Min Range: -7.9228
Max Act: 7.1728. Min Act: -0.1700
Data Index: 5036896 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9228. Min Range: -7.9228
Max Act: 7.1728. Min Act: -0.1700
Data Index: 7690125 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9228. Min Range: -7.9228
Max Act: 7.1728. Min Act: -0.1700
Data Index: 633329 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9228. Min Range: -7.9228
Max Act: 7.1416. Min Act: -0.1700
Data Index: 5244164 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9228. Min Range: -7.9228
Max Act: 7.0791. Min Act: -0.1700
Data Index: 6952386 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9228. Min Range: -7.9228
Max Act: 7.0791. Min Act: -0.1700
Data Index: 603138 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9228. Min Range: -7.9228
Max Act: 7.0791. Min Act: -0.1700
Data Index: 2914390 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9228. Min Range: -7.9228
Max Act: 7.1103. Min Act: -0.1700
Data Index: 2341948 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9228. Min Range: -7.9228
Max Act: 7.0791. Min Act: -0.1700
Data Index: 5545238 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9228. Min Range: -7.9228
Max Act: 7.0791. Min Act: -0.1700
Data Index: 6153092 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9228. Min Range: -7.9228
Max Act: 7.0478. Min Act: -0.1700
Data Index: 2266378 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19