Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2534 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7421. Min Range: -2.7421
Max Act: 2.7421. Min Act: -0.1700
Data Index: 1764001 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7421. Min Range: -2.7421
Max Act: 2.7421. Min Act: -0.1700
Data Index: 6740167 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7421. Min Range: -2.7421
Max Act: 2.7421. Min Act: -0.1700
Data Index: 3877996 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7421. Min Range: -2.7421
Max Act: 2.7102. Min Act: -0.1700
Data Index: 7901964 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7421. Min Range: -2.7421
Max Act: 2.6942. Min Act: -0.1700
Data Index: 2006446 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7421. Min Range: -2.7421
Max Act: 2.6942. Min Act: -0.1700
Data Index: 2161003 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7421. Min Range: -2.7421
Max Act: 2.6942. Min Act: -0.1700
Data Index: 2473415 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7421. Min Range: -2.7421
Max Act: 2.6942. Min Act: -0.1700
Data Index: 1196541 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7421. Min Range: -2.7421
Max Act: 2.7102. Min Act: -0.1700
Data Index: 633592 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7421. Min Range: -2.7421
Max Act: 2.6621. Min Act: -0.1700
Data Index: 2462306 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7421. Min Range: -2.7421
Max Act: 2.6621. Min Act: -0.1700
Data Index: 2781370 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7421. Min Range: -2.7421
Max Act: 2.6621. Min Act: -0.1700
Data Index: 6126885 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7421. Min Range: -2.7421
Max Act: 2.6621. Min Act: -0.1700
Data Index: 3533951 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7421. Min Range: -2.7421
Max Act: 2.6621. Min Act: -0.1700
Data Index: 615614 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7421. Min Range: -2.7421
Max Act: 2.6461. Min Act: -0.1700
Data Index: 6118444 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7421. Min Range: -2.7421
Max Act: 2.6461. Min Act: -0.1700
Data Index: 2414197 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7421. Min Range: -2.7421
Max Act: 2.6461. Min Act: -0.1700
Data Index: 5266290 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7421. Min Range: -2.7421
Max Act: 2.6621. Min Act: -0.1700
Data Index: 1775851 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7421. Min Range: -2.7421
Max Act: 2.6461. Min Act: -0.1700
Data Index: 1649006 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7421. Min Range: -2.7421
Max Act: 2.6461. Min Act: -0.1700
Data Index: 1595762 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19