Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4973 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3341. Min Range: -4.3341
Max Act: 4.3341. Min Act: -0.1700
Data Index: 6669644 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3341. Min Range: -4.3341
Max Act: 4.3341. Min Act: -0.1700
Data Index: 6215003 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3341. Min Range: -4.3341
Max Act: 4.1465. Min Act: -0.1700
Data Index: 452281 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3341. Min Range: -4.3341
Max Act: 4.1465. Min Act: -0.1700
Data Index: 1573768 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3341. Min Range: -4.3341
Max Act: 4.1465. Min Act: -0.1700
Data Index: 111884 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3341. Min Range: -4.3341
Max Act: 4.0840. Min Act: -0.1700
Data Index: 5810006 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3341. Min Range: -4.3341
Max Act: 4.0840. Min Act: -0.1700
Data Index: 5161675 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3341. Min Range: -4.3341
Max Act: 4.0840. Min Act: -0.1700
Data Index: 6669645 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3341. Min Range: -4.3341
Max Act: 4.0840. Min Act: -0.1700
Data Index: 6528434 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3341. Min Range: -4.3341
Max Act: 4.0528. Min Act: -0.1700
Data Index: 2190779 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3341. Min Range: -4.3341
Max Act: 4.0528. Min Act: -0.1700
Data Index: 5266420 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3341. Min Range: -4.3341
Max Act: 4.0528. Min Act: -0.1700
Data Index: 3899157 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3341. Min Range: -4.3341
Max Act: 4.0528. Min Act: -0.1700
Data Index: 3826863 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3341. Min Range: -4.3341
Max Act: 4.0528. Min Act: -0.1700
Data Index: 3625174 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3341. Min Range: -4.3341
Max Act: 3.9903. Min Act: -0.1700
Data Index: 327743 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3341. Min Range: -4.3341
Max Act: 4.0215. Min Act: -0.1700
Data Index: 2220228 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3341. Min Range: -4.3341
Max Act: 4.0215. Min Act: -0.1700
Data Index: 6683538 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3341. Min Range: -4.3341
Max Act: 4.0215. Min Act: -0.1700
Data Index: 1123974 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3341. Min Range: -4.3341
Max Act: 4.0215. Min Act: -0.1700
Data Index: 3482067 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3341. Min Range: -4.3341
Max Act: 4.0215. Min Act: -0.1700
Data Index: 3497258 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19