Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 921 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2408. Min Range: -6.2408
Max Act: 6.2408. Min Act: -0.1700
Data Index: 6497625 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2408. Min Range: -6.2408
Max Act: 6.1471. Min Act: -0.1700
Data Index: 5813004 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2408. Min Range: -6.2408
Max Act: 6.0221. Min Act: -0.1700
Data Index: 8321664 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2408. Min Range: -6.2408
Max Act: 5.9908. Min Act: -0.1700
Data Index: 1613662 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2408. Min Range: -6.2408
Max Act: 5.9283. Min Act: -0.1700
Data Index: 7714194 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2408. Min Range: -6.2408
Max Act: 5.8658. Min Act: -0.1700
Data Index: 2016866 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2408. Min Range: -6.2408
Max Act: 5.8346. Min Act: -0.1700
Data Index: 4153253 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2408. Min Range: -6.2408
Max Act: 5.8346. Min Act: -0.1700
Data Index: 2690074 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2408. Min Range: -6.2408
Max Act: 5.8033. Min Act: -0.1700
Data Index: 1122570 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2408. Min Range: -6.2408
Max Act: 5.8346. Min Act: -0.1700
Data Index: 2728767 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2408. Min Range: -6.2408
Max Act: 5.8346. Min Act: -0.1700
Data Index: 2335284 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2408. Min Range: -6.2408
Max Act: 5.8033. Min Act: -0.1700
Data Index: 7727101 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2408. Min Range: -6.2408
Max Act: 5.8033. Min Act: -0.1700
Data Index: 2696723 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2408. Min Range: -6.2408
Max Act: 5.8033. Min Act: -0.1700
Data Index: 34255 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2408. Min Range: -6.2408
Max Act: 5.7721. Min Act: -0.1700
Data Index: 7167933 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2408. Min Range: -6.2408
Max Act: 5.7721. Min Act: -0.1700
Data Index: 7375231 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2408. Min Range: -6.2408
Max Act: 5.7721. Min Act: -0.1700
Data Index: 4890695 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2408. Min Range: -6.2408
Max Act: 5.7721. Min Act: -0.1700
Data Index: 3449193 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2408. Min Range: -6.2408
Max Act: 5.7721. Min Act: -0.1700
Data Index: 5552278 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2408. Min Range: -6.2408
Max Act: 5.7721. Min Act: -0.1700
Data Index: 180503 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19