Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1953 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2544. Min Range: -5.2544
Max Act: 5.2544. Min Act: -0.1700
Data Index: 2221538 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2544. Min Range: -5.2544
Max Act: 5.2544. Min Act: -0.1700
Data Index: 1833785 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2544. Min Range: -5.2544
Max Act: 5.2231. Min Act: -0.1700
Data Index: 468169 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2544. Min Range: -5.2544
Max Act: 5.1919. Min Act: -0.1700
Data Index: 2509063 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2544. Min Range: -5.2544
Max Act: 5.0981. Min Act: -0.1700
Data Index: 4042620 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2544. Min Range: -5.2544
Max Act: 5.0669. Min Act: -0.1700
Data Index: 7920703 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2544. Min Range: -5.2544
Max Act: 5.0356. Min Act: -0.1700
Data Index: 5338172 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2544. Min Range: -5.2544
Max Act: 5.0356. Min Act: -0.1700
Data Index: 4916402 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2544. Min Range: -5.2544
Max Act: 5.0356. Min Act: -0.1700
Data Index: 5716107 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2544. Min Range: -5.2544
Max Act: 5.0044. Min Act: -0.1700
Data Index: 5023985 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2544. Min Range: -5.2544
Max Act: 5.0044. Min Act: -0.1700
Data Index: 3546736 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2544. Min Range: -5.2544
Max Act: 4.9731. Min Act: -0.1700
Data Index: 8657411 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2544. Min Range: -5.2544
Max Act: 4.9731. Min Act: -0.1700
Data Index: 1905241 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2544. Min Range: -5.2544
Max Act: 4.9419. Min Act: -0.1700
Data Index: 6478850 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2544. Min Range: -5.2544
Max Act: 4.9419. Min Act: -0.1700
Data Index: 2852817 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2544. Min Range: -5.2544
Max Act: 4.9419. Min Act: -0.1700
Data Index: 579667 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2544. Min Range: -5.2544
Max Act: 4.9106. Min Act: -0.1700
Data Index: 4346917 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2544. Min Range: -5.2544
Max Act: 4.9106. Min Act: -0.1700
Data Index: 2558218 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2544. Min Range: -5.2544
Max Act: 4.9106. Min Act: -0.1700
Data Index: 7510853 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2544. Min Range: -5.2544
Max Act: 4.8794. Min Act: -0.1700
Data Index: 2315693 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #19