Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3340 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1380. Min Range: -10.1380
Max Act: 10.1380. Min Act: -0.1700
Data Index: 2434163 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1380. Min Range: -10.1380
Max Act: 9.6380. Min Act: -0.1700
Data Index: 2288796 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1380. Min Range: -10.1380
Max Act: 9.5755. Min Act: -0.1700
Data Index: 8676555 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1380. Min Range: -10.1380
Max Act: 9.5130. Min Act: -0.1700
Data Index: 3314943 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1380. Min Range: -10.1380
Max Act: 9.4505. Min Act: -0.1700
Data Index: 1324701 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1380. Min Range: -10.1380
Max Act: 9.4505. Min Act: -0.1700
Data Index: 401892 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1380. Min Range: -10.1380
Max Act: 9.4505. Min Act: -0.1700
Data Index: 1134789 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1380. Min Range: -10.1380
Max Act: 9.3880. Min Act: -0.1700
Data Index: 1437371 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1380. Min Range: -10.1380
Max Act: 9.3880. Min Act: -0.1700
Data Index: 5974680 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1380. Min Range: -10.1380
Max Act: 9.3255. Min Act: -0.1700
Data Index: 6300437 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1380. Min Range: -10.1380
Max Act: 9.3255. Min Act: -0.1700
Data Index: 1231792 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1380. Min Range: -10.1380
Max Act: 9.3255. Min Act: -0.1700
Data Index: 6974072 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1380. Min Range: -10.1380
Max Act: 9.3880. Min Act: -0.1700
Data Index: 6025632 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1380. Min Range: -10.1380
Max Act: 9.3255. Min Act: -0.1700
Data Index: 968353 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1380. Min Range: -10.1380
Max Act: 9.2630. Min Act: -0.1700
Data Index: 3802982 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1380. Min Range: -10.1380
Max Act: 9.2630. Min Act: -0.1700
Data Index: 987957 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1380. Min Range: -10.1380
Max Act: 9.2630. Min Act: -0.1700
Data Index: 669700 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1380. Min Range: -10.1380
Max Act: 9.2005. Min Act: -0.1700
Data Index: 1724193 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1380. Min Range: -10.1380
Max Act: 9.2005. Min Act: -0.1700
Data Index: 5387654 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1380. Min Range: -10.1380
Max Act: 9.2005. Min Act: -0.1700
Data Index: 780631 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19