Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2426 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.1700. Min Range: -11.1700
Max Act: 11.1700. Min Act: -0.1700
Data Index: 1030877 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1700. Min Range: -11.1700
Max Act: 11.1075. Min Act: -0.1700
Data Index: 8403839 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1700. Min Range: -11.1700
Max Act: 11.0450. Min Act: -0.1700
Data Index: 542687 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1700. Min Range: -11.1700
Max Act: 10.9825. Min Act: -0.1700
Data Index: 4887363 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1700. Min Range: -11.1700
Max Act: 10.7325. Min Act: -0.1700
Data Index: 938322 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1700. Min Range: -11.1700
Max Act: 10.6700. Min Act: -0.1700
Data Index: 7558316 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1700. Min Range: -11.1700
Max Act: 10.5450. Min Act: -0.1700
Data Index: 6361671 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1700. Min Range: -11.1700
Max Act: 10.5450. Min Act: -0.1700
Data Index: 6389779 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1700. Min Range: -11.1700
Max Act: 10.3575. Min Act: -0.1700
Data Index: 5198084 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1700. Min Range: -11.1700
Max Act: 10.2950. Min Act: -0.1700
Data Index: 7985579 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1700. Min Range: -11.1700
Max Act: 10.2950. Min Act: -0.1700
Data Index: 2242850 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1700. Min Range: -11.1700
Max Act: 10.2950. Min Act: -0.1700
Data Index: 6361673 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1700. Min Range: -11.1700
Max Act: 10.2325. Min Act: -0.1700
Data Index: 3169809 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1700. Min Range: -11.1700
Max Act: 10.2325. Min Act: -0.1700
Data Index: 4205662 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1700. Min Range: -11.1700
Max Act: 10.2325. Min Act: -0.1700
Data Index: 713460 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1700. Min Range: -11.1700
Max Act: 10.2325. Min Act: -0.1700
Data Index: 4144690 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1700. Min Range: -11.1700
Max Act: 10.2325. Min Act: -0.1700
Data Index: 2830717 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1700. Min Range: -11.1700
Max Act: 10.1700. Min Act: -0.1700
Data Index: 1984709 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1700. Min Range: -11.1700
Max Act: 10.1700. Min Act: -0.1700
Data Index: 6055489 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1700. Min Range: -11.1700
Max Act: 10.1700. Min Act: -0.1700
Data Index: 3485814 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19