Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 601 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.5693. Min Act: -0.1700
Data Index: 8367410 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.5380. Min Act: -0.1700
Data Index: 23090 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.4443. Min Act: -0.1700
Data Index: 8826654 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.3193. Min Act: -0.1700
Data Index: 3132855 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.3193. Min Act: -0.1700
Data Index: 5639607 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.3193. Min Act: -0.1700
Data Index: 6814815 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.2255. Min Act: -0.1700
Data Index: 3359934 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.1943. Min Act: -0.1700
Data Index: 4973033 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.2255. Min Act: -0.1700
Data Index: 3269391 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.1943. Min Act: -0.1700
Data Index: 3870007 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.2255. Min Act: -0.1700
Data Index: 851517 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.1630. Min Act: -0.1700
Data Index: 94170 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.1630. Min Act: -0.1700
Data Index: 7193635 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.1630. Min Act: -0.1700
Data Index: 5850443 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.1318. Min Act: -0.1700
Data Index: 6733888 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.1318. Min Act: -0.1700
Data Index: 2948075 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.1005. Min Act: -0.1700
Data Index: 271200 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.1005. Min Act: -0.1700
Data Index: 3018943 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.0693. Min Act: -0.1700
Data Index: 6668599 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5693. Min Range: -6.5693
Max Act: 6.0693. Min Act: -0.1700
Data Index: 2831985 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19