Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1655 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1347. Min Range: -4.1347
Max Act: 4.1347. Min Act: -0.1700
Data Index: 8301696 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1347. Min Range: -4.1347
Max Act: 4.0722. Min Act: -0.1700
Data Index: 7115643 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1347. Min Range: -4.1347
Max Act: 4.1035. Min Act: -0.1700
Data Index: 6149 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1347. Min Range: -4.1347
Max Act: 3.9472. Min Act: -0.1700
Data Index: 5740278 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1347. Min Range: -4.1347
Max Act: 3.9784. Min Act: -0.1700
Data Index: 8372183 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1347. Min Range: -4.1347
Max Act: 3.9472. Min Act: -0.1700
Data Index: 6843710 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1347. Min Range: -4.1347
Max Act: 3.8846. Min Act: -0.1700
Data Index: 5740275 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1347. Min Range: -4.1347
Max Act: 3.8534. Min Act: -0.1700
Data Index: 3160073 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1347. Min Range: -4.1347
Max Act: 3.8846. Min Act: -0.1700
Data Index: 6843709 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1347. Min Range: -4.1347
Max Act: 3.8221. Min Act: -0.1700
Data Index: 4773436 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1347. Min Range: -4.1347
Max Act: 3.8534. Min Act: -0.1700
Data Index: 6870443 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1347. Min Range: -4.1347
Max Act: 3.7908. Min Act: -0.1700
Data Index: 2045355 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1347. Min Range: -4.1347
Max Act: 3.8221. Min Act: -0.1700
Data Index: 5147467 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1347. Min Range: -4.1347
Max Act: 3.8221. Min Act: -0.1700
Data Index: 875517 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1347. Min Range: -4.1347
Max Act: 3.7908. Min Act: -0.1700
Data Index: 5382476 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1347. Min Range: -4.1347
Max Act: 3.8221. Min Act: -0.1700
Data Index: 1891346 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1347. Min Range: -4.1347
Max Act: 3.8221. Min Act: -0.1700
Data Index: 5800311 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1347. Min Range: -4.1347
Max Act: 3.7596. Min Act: -0.1700
Data Index: 4199215 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1347. Min Range: -4.1347
Max Act: 3.7596. Min Act: -0.1700
Data Index: 1673312 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1347. Min Range: -4.1347
Max Act: 3.7596. Min Act: -0.1700
Data Index: 765511 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #19