Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2275 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9283. Min Range: -7.9283
Max Act: 7.9283. Min Act: -0.1700
Data Index: 741436 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9283. Min Range: -7.9283
Max Act: 7.6471. Min Act: -0.1700
Data Index: 7325370 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9283. Min Range: -7.9283
Max Act: 7.5846. Min Act: -0.1700
Data Index: 6479604 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9283. Min Range: -7.9283
Max Act: 7.5533. Min Act: -0.1700
Data Index: 5392148 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9283. Min Range: -7.9283
Max Act: 7.5533. Min Act: -0.1700
Data Index: 4525169 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9283. Min Range: -7.9283
Max Act: 7.5221. Min Act: -0.1700
Data Index: 222540 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9283. Min Range: -7.9283
Max Act: 7.4596. Min Act: -0.1700
Data Index: 2703624 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9283. Min Range: -7.9283
Max Act: 7.3971. Min Act: -0.1700
Data Index: 3334174 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9283. Min Range: -7.9283
Max Act: 7.3971. Min Act: -0.1700
Data Index: 4326580 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9283. Min Range: -7.9283
Max Act: 7.3971. Min Act: -0.1700
Data Index: 4910320 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9283. Min Range: -7.9283
Max Act: 7.3971. Min Act: -0.1700
Data Index: 576757 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9283. Min Range: -7.9283
Max Act: 7.3346. Min Act: -0.1700
Data Index: 5570946 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9283. Min Range: -7.9283
Max Act: 7.3346. Min Act: -0.1700
Data Index: 356547 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9283. Min Range: -7.9283
Max Act: 7.3346. Min Act: -0.1700
Data Index: 4869913 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9283. Min Range: -7.9283
Max Act: 7.3346. Min Act: -0.1700
Data Index: 2503866 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9283. Min Range: -7.9283
Max Act: 7.3346. Min Act: -0.1700
Data Index: 5255958 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9283. Min Range: -7.9283
Max Act: 7.3346. Min Act: -0.1700
Data Index: 868136 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9283. Min Range: -7.9283
Max Act: 7.3346. Min Act: -0.1700
Data Index: 3159963 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9283. Min Range: -7.9283
Max Act: 7.3346. Min Act: -0.1700
Data Index: 3206101 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9283. Min Range: -7.9283
Max Act: 7.3346. Min Act: -0.1700
Data Index: 6448507 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19