Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5974 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3292. Min Range: -6.3292
Max Act: 6.3292. Min Act: -0.1700
Data Index: 2140844 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3292. Min Range: -6.3292
Max Act: 6.2042. Min Act: -0.1700
Data Index: 7523369 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3292. Min Range: -6.3292
Max Act: 6.0167. Min Act: -0.1700
Data Index: 3785308 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3292. Min Range: -6.3292
Max Act: 5.9854. Min Act: -0.1700
Data Index: 5149063 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3292. Min Range: -6.3292
Max Act: 5.9854. Min Act: -0.1700
Data Index: 365915 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3292. Min Range: -6.3292
Max Act: 5.9542. Min Act: -0.1700
Data Index: 4287909 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3292. Min Range: -6.3292
Max Act: 5.8917. Min Act: -0.1700
Data Index: 5860146 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3292. Min Range: -6.3292
Max Act: 5.9229. Min Act: -0.1700
Data Index: 6226409 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3292. Min Range: -6.3292
Max Act: 5.8917. Min Act: -0.1700
Data Index: 2978789 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3292. Min Range: -6.3292
Max Act: 5.8917. Min Act: -0.1700
Data Index: 4604702 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3292. Min Range: -6.3292
Max Act: 5.8604. Min Act: -0.1700
Data Index: 118040 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3292. Min Range: -6.3292
Max Act: 5.8604. Min Act: -0.1700
Data Index: 3830108 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3292. Min Range: -6.3292
Max Act: 5.8604. Min Act: -0.1700
Data Index: 2400905 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3292. Min Range: -6.3292
Max Act: 5.8604. Min Act: -0.1700
Data Index: 5485842 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3292. Min Range: -6.3292
Max Act: 5.8604. Min Act: -0.1700
Data Index: 8116883 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3292. Min Range: -6.3292
Max Act: 5.8292. Min Act: -0.1700
Data Index: 1771120 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3292. Min Range: -6.3292
Max Act: 5.8292. Min Act: -0.1700
Data Index: 8729886 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3292. Min Range: -6.3292
Max Act: 5.8292. Min Act: -0.1700
Data Index: 7941028 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3292. Min Range: -6.3292
Max Act: 5.7979. Min Act: -0.1700
Data Index: 6351446 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3292. Min Range: -6.3292
Max Act: 5.7979. Min Act: -0.1700
Data Index: 2862714 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19