Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3413 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3955. Min Range: -3.3955
Max Act: 3.3955. Min Act: -0.1700
Data Index: 5965379 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3955. Min Range: -3.3955
Max Act: 3.3642. Min Act: -0.1700
Data Index: 1377881 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3955. Min Range: -3.3955
Max Act: 3.2386. Min Act: -0.1700
Data Index: 1388422 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3955. Min Range: -3.3955
Max Act: 3.2229. Min Act: -0.1700
Data Index: 4180093 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3955. Min Range: -3.3955
Max Act: 3.1599. Min Act: -0.1700
Data Index: 7646941 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3955. Min Range: -3.3955
Max Act: 3.1284. Min Act: -0.1700
Data Index: 7608170 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3955. Min Range: -3.3955
Max Act: 3.1442. Min Act: -0.1700
Data Index: 5402297 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3955. Min Range: -3.3955
Max Act: 3.0969. Min Act: -0.1700
Data Index: 6221370 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3955. Min Range: -3.3955
Max Act: 3.1127. Min Act: -0.1700
Data Index: 8371837 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3955. Min Range: -3.3955
Max Act: 3.1127. Min Act: -0.1700
Data Index: 4180094 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3955. Min Range: -3.3955
Max Act: 3.0812. Min Act: -0.1700
Data Index: 5273357 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3955. Min Range: -3.3955
Max Act: 3.0654. Min Act: -0.1700
Data Index: 4138584 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3955. Min Range: -3.3955
Max Act: 3.0496. Min Act: -0.1700
Data Index: 1434856 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3955. Min Range: -3.3955
Max Act: 3.0496. Min Act: -0.1700
Data Index: 7028558 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3955. Min Range: -3.3955
Max Act: 3.0338. Min Act: -0.1700
Data Index: 7271023 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3955. Min Range: -3.3955
Max Act: 3.0338. Min Act: -0.1700
Data Index: 7473041 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3955. Min Range: -3.3955
Max Act: 3.0338. Min Act: -0.1700
Data Index: 283256 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3955. Min Range: -3.3955
Max Act: 3.0180. Min Act: -0.1700
Data Index: 6205879 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3955. Min Range: -3.3955
Max Act: 3.0338. Min Act: -0.1700
Data Index: 1929644 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3955. Min Range: -3.3955
Max Act: 3.0180. Min Act: -0.1700
Data Index: 3502095 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19