Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4603 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8707. Min Range: -6.8707
Max Act: 6.8707. Min Act: -0.1700
Data Index: 6762849 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8707. Min Range: -6.8707
Max Act: 6.7457. Min Act: -0.1700
Data Index: 1492756 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8707. Min Range: -6.8707
Max Act: 6.6207. Min Act: -0.1700
Data Index: 5305272 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8707. Min Range: -6.8707
Max Act: 6.6207. Min Act: -0.1700
Data Index: 3605077 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8707. Min Range: -6.8707
Max Act: 6.5895. Min Act: -0.1700
Data Index: 4437669 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8707. Min Range: -6.8707
Max Act: 6.5582. Min Act: -0.1700
Data Index: 3848525 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8707. Min Range: -6.8707
Max Act: 6.5895. Min Act: -0.1700
Data Index: 5500675 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8707. Min Range: -6.8707
Max Act: 6.5270. Min Act: -0.1700
Data Index: 4156273 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8707. Min Range: -6.8707
Max Act: 6.5270. Min Act: -0.1700
Data Index: 8178572 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8707. Min Range: -6.8707
Max Act: 6.5270. Min Act: -0.1700
Data Index: 2231730 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8707. Min Range: -6.8707
Max Act: 6.4957. Min Act: -0.1700
Data Index: 7471612 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8707. Min Range: -6.8707
Max Act: 6.4957. Min Act: -0.1700
Data Index: 8722930 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8707. Min Range: -6.8707
Max Act: 6.4645. Min Act: -0.1700
Data Index: 1846221 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8707. Min Range: -6.8707
Max Act: 6.4645. Min Act: -0.1700
Data Index: 3344420 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8707. Min Range: -6.8707
Max Act: 6.4332. Min Act: -0.1700
Data Index: 1238703 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8707. Min Range: -6.8707
Max Act: 6.4332. Min Act: -0.1700
Data Index: 1157287 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8707. Min Range: -6.8707
Max Act: 6.4020. Min Act: -0.1700
Data Index: 5290631 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8707. Min Range: -6.8707
Max Act: 6.3707. Min Act: -0.1700
Data Index: 2994112 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8707. Min Range: -6.8707
Max Act: 6.4020. Min Act: -0.1700
Data Index: 2916076 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8707. Min Range: -6.8707
Max Act: 6.4020. Min Act: -0.1700
Data Index: 2518396 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19