Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3062 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1788. Min Range: -5.1788
Max Act: 5.1788. Min Act: -0.1700
Data Index: 2056416 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1788. Min Range: -5.1788
Max Act: 5.1475. Min Act: -0.1700
Data Index: 1552580 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1788. Min Range: -5.1788
Max Act: 5.1163. Min Act: -0.1700
Data Index: 5915166 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1788. Min Range: -5.1788
Max Act: 5.0538. Min Act: -0.1700
Data Index: 3338643 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1788. Min Range: -5.1788
Max Act: 5.0225. Min Act: -0.1700
Data Index: 6485720 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1788. Min Range: -5.1788
Max Act: 4.9913. Min Act: -0.1700
Data Index: 8824158 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1788. Min Range: -5.1788
Max Act: 5.0225. Min Act: -0.1700
Data Index: 4585453 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1788. Min Range: -5.1788
Max Act: 4.9913. Min Act: -0.1700
Data Index: 89169 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1788. Min Range: -5.1788
Max Act: 4.9913. Min Act: -0.1700
Data Index: 5896652 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1788. Min Range: -5.1788
Max Act: 4.9288. Min Act: -0.1700
Data Index: 8714013 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1788. Min Range: -5.1788
Max Act: 4.9600. Min Act: -0.1700
Data Index: 2067431 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1788. Min Range: -5.1788
Max Act: 4.9288. Min Act: -0.1700
Data Index: 1443887 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1788. Min Range: -5.1788
Max Act: 4.9288. Min Act: -0.1700
Data Index: 1554954 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1788. Min Range: -5.1788
Max Act: 4.9288. Min Act: -0.1700
Data Index: 4154281 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1788. Min Range: -5.1788
Max Act: 4.9288. Min Act: -0.1700
Data Index: 3640797 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1788. Min Range: -5.1788
Max Act: 4.8975. Min Act: -0.1700
Data Index: 6614661 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1788. Min Range: -5.1788
Max Act: 4.8975. Min Act: -0.1700
Data Index: 1893368 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1788. Min Range: -5.1788
Max Act: 4.9288. Min Act: -0.1700
Data Index: 7245768 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1788. Min Range: -5.1788
Max Act: 4.8975. Min Act: -0.1700
Data Index: 8522977 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1788. Min Range: -5.1788
Max Act: 4.8975. Min Act: -0.1700
Data Index: 2616398 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19