Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3534 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5291. Min Range: -7.5291
Max Act: 7.5291. Min Act: -0.1700
Data Index: 210397 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5291. Min Range: -7.5291
Max Act: 7.3416. Min Act: -0.1700
Data Index: 5286380 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5291. Min Range: -7.5291
Max Act: 7.3416. Min Act: -0.1700
Data Index: 3195355 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5291. Min Range: -7.5291
Max Act: 7.2478. Min Act: -0.1700
Data Index: 7251 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5291. Min Range: -7.5291
Max Act: 7.2166. Min Act: -0.1700
Data Index: 493678 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5291. Min Range: -7.5291
Max Act: 7.2478. Min Act: -0.1700
Data Index: 7107989 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5291. Min Range: -7.5291
Max Act: 7.1853. Min Act: -0.1700
Data Index: 4100436 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5291. Min Range: -7.5291
Max Act: 7.0916. Min Act: -0.1700
Data Index: 2091991 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5291. Min Range: -7.5291
Max Act: 7.0916. Min Act: -0.1700
Data Index: 1546986 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5291. Min Range: -7.5291
Max Act: 7.0291. Min Act: -0.1700
Data Index: 2065535 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5291. Min Range: -7.5291
Max Act: 7.0603. Min Act: -0.1700
Data Index: 3910782 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5291. Min Range: -7.5291
Max Act: 7.0291. Min Act: -0.1700
Data Index: 5076053 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5291. Min Range: -7.5291
Max Act: 7.0291. Min Act: -0.1700
Data Index: 6003767 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5291. Min Range: -7.5291
Max Act: 7.0291. Min Act: -0.1700
Data Index: 5531241 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5291. Min Range: -7.5291
Max Act: 6.9978. Min Act: -0.1700
Data Index: 8081299 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5291. Min Range: -7.5291
Max Act: 6.9978. Min Act: -0.1700
Data Index: 6743527 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5291. Min Range: -7.5291
Max Act: 6.9978. Min Act: -0.1700
Data Index: 5933469 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5291. Min Range: -7.5291
Max Act: 6.9978. Min Act: -0.1700
Data Index: 3923419 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5291. Min Range: -7.5291
Max Act: 6.9666. Min Act: -0.1700
Data Index: 1270532 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5291. Min Range: -7.5291
Max Act: 6.9978. Min Act: -0.1700
Data Index: 8001068 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19