Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4938 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3461. Min Range: -6.3461
Max Act: 6.3461. Min Act: -0.1700
Data Index: 5307163 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3461. Min Range: -6.3461
Max Act: 6.1898. Min Act: -0.1700
Data Index: 344955 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3461. Min Range: -6.3461
Max Act: 6.1273. Min Act: -0.1700
Data Index: 37333 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3461. Min Range: -6.3461
Max Act: 6.0961. Min Act: -0.1700
Data Index: 7610385 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3461. Min Range: -6.3461
Max Act: 6.0961. Min Act: -0.1700
Data Index: 6975589 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3461. Min Range: -6.3461
Max Act: 5.9086. Min Act: -0.1700
Data Index: 2204781 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3461. Min Range: -6.3461
Max Act: 5.9086. Min Act: -0.1700
Data Index: 8548362 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3461. Min Range: -6.3461
Max Act: 5.8773. Min Act: -0.1700
Data Index: 73729 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3461. Min Range: -6.3461
Max Act: 5.8148. Min Act: -0.1700
Data Index: 4608206 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3461. Min Range: -6.3461
Max Act: 5.8148. Min Act: -0.1700
Data Index: 7593423 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3461. Min Range: -6.3461
Max Act: 5.7836. Min Act: -0.1700
Data Index: 1542304 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3461. Min Range: -6.3461
Max Act: 5.7211. Min Act: -0.1700
Data Index: 1624503 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3461. Min Range: -6.3461
Max Act: 5.7523. Min Act: -0.1700
Data Index: 7534681 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3461. Min Range: -6.3461
Max Act: 5.7523. Min Act: -0.1700
Data Index: 8276265 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3461. Min Range: -6.3461
Max Act: 5.7211. Min Act: -0.1700
Data Index: 4953356 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3461. Min Range: -6.3461
Max Act: 5.7523. Min Act: -0.1700
Data Index: 5152659 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3461. Min Range: -6.3461
Max Act: 5.7211. Min Act: -0.1700
Data Index: 2290528 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3461. Min Range: -6.3461
Max Act: 5.6898. Min Act: -0.1700
Data Index: 4165503 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3461. Min Range: -6.3461
Max Act: 5.7211. Min Act: -0.1700
Data Index: 7738804 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3461. Min Range: -6.3461
Max Act: 5.7211. Min Act: -0.1700
Data Index: 6843379 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19