Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4708 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.9582. Min Act: -0.1700
Data Index: 5390114 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.9269. Min Act: -0.1700
Data Index: 4048460 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.5519. Min Act: -0.1700
Data Index: 8592417 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.5207. Min Act: -0.1700
Data Index: 2394622 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.4894. Min Act: -0.1700
Data Index: 7245664 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.4894. Min Act: -0.1700
Data Index: 5302295 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.4582. Min Act: -0.1700
Data Index: 7518711 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.4582. Min Act: -0.1700
Data Index: 695669 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.4582. Min Act: -0.1700
Data Index: 4290708 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.4894. Min Act: -0.1700
Data Index: 2400698 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.4269. Min Act: -0.1700
Data Index: 6775897 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.4269. Min Act: -0.1700
Data Index: 1833206 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.3957. Min Act: -0.1700
Data Index: 8030525 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.3957. Min Act: -0.1700
Data Index: 6802604 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.3957. Min Act: -0.1700
Data Index: 8239252 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.3957. Min Act: -0.1700
Data Index: 6157593 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.3644. Min Act: -0.1700
Data Index: 409433 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.3644. Min Act: -0.1700
Data Index: 6445460 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.3644. Min Act: -0.1700
Data Index: 5716407 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9582. Min Range: -4.9582
Max Act: 4.3644. Min Act: -0.1700
Data Index: 356834 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19