Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2527 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3480. Min Range: -3.3480
Max Act: 3.3480. Min Act: -0.1700
Data Index: 282209 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3480. Min Range: -3.3480
Max Act: 3.3323. Min Act: -0.1700
Data Index: 5126532 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3480. Min Range: -3.3480
Max Act: 3.3009. Min Act: -0.1700
Data Index: 3124531 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3480. Min Range: -3.3480
Max Act: 3.2695. Min Act: -0.1700
Data Index: 7123083 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3480. Min Range: -3.3480
Max Act: 3.2538. Min Act: -0.1700
Data Index: 739213 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3480. Min Range: -3.3480
Max Act: 3.2538. Min Act: -0.1700
Data Index: 4153104 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3480. Min Range: -3.3480
Max Act: 3.2223. Min Act: -0.1700
Data Index: 3211401 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3480. Min Range: -3.3480
Max Act: 3.2380. Min Act: -0.1700
Data Index: 8409072 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3480. Min Range: -3.3480
Max Act: 3.2380. Min Act: -0.1700
Data Index: 1133422 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3480. Min Range: -3.3480
Max Act: 3.2223. Min Act: -0.1700
Data Index: 815911 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3480. Min Range: -3.3480
Max Act: 3.1594. Min Act: -0.1700
Data Index: 6356700 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3480. Min Range: -3.3480
Max Act: 3.1594. Min Act: -0.1700
Data Index: 6918534 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3480. Min Range: -3.3480
Max Act: 3.1437. Min Act: -0.1700
Data Index: 1879620 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3480. Min Range: -3.3480
Max Act: 3.1279. Min Act: -0.1700
Data Index: 6408148 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3480. Min Range: -3.3480
Max Act: 3.1279. Min Act: -0.1700
Data Index: 2426679 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3480. Min Range: -3.3480
Max Act: 3.1122. Min Act: -0.1700
Data Index: 4179837 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3480. Min Range: -3.3480
Max Act: 3.1279. Min Act: -0.1700
Data Index: 3124522 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3480. Min Range: -3.3480
Max Act: 3.1279. Min Act: -0.1700
Data Index: 7865226 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3480. Min Range: -3.3480
Max Act: 3.1122. Min Act: -0.1700
Data Index: 5862995 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3480. Min Range: -3.3480
Max Act: 3.0964. Min Act: -0.1700
Data Index: 6222278 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19