Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1505 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4385. Min Range: -5.4385
Max Act: 5.4385. Min Act: -0.1700
Data Index: 6039004 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4385. Min Range: -5.4385
Max Act: 5.3448. Min Act: -0.1700
Data Index: 7180414 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4385. Min Range: -5.4385
Max Act: 5.3448. Min Act: -0.1700
Data Index: 4609731 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4385. Min Range: -5.4385
Max Act: 5.3135. Min Act: -0.1700
Data Index: 8563435 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4385. Min Range: -5.4385
Max Act: 5.2823. Min Act: -0.1700
Data Index: 1291499 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4385. Min Range: -5.4385
Max Act: 5.3135. Min Act: -0.1700
Data Index: 8563438 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4385. Min Range: -5.4385
Max Act: 5.2510. Min Act: -0.1700
Data Index: 7237121 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4385. Min Range: -5.4385
Max Act: 5.1885. Min Act: -0.1700
Data Index: 5460720 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4385. Min Range: -5.4385
Max Act: 5.1573. Min Act: -0.1700
Data Index: 3650697 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4385. Min Range: -5.4385
Max Act: 5.1573. Min Act: -0.1700
Data Index: 6314077 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4385. Min Range: -5.4385
Max Act: 5.1573. Min Act: -0.1700
Data Index: 4418583 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4385. Min Range: -5.4385
Max Act: 5.0948. Min Act: -0.1700
Data Index: 4434788 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4385. Min Range: -5.4385
Max Act: 5.0948. Min Act: -0.1700
Data Index: 6542510 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4385. Min Range: -5.4385
Max Act: 5.0635. Min Act: -0.1700
Data Index: 6709203 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4385. Min Range: -5.4385
Max Act: 5.0635. Min Act: -0.1700
Data Index: 7533699 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4385. Min Range: -5.4385
Max Act: 5.0948. Min Act: -0.1700
Data Index: 6827321 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4385. Min Range: -5.4385
Max Act: 5.0635. Min Act: -0.1700
Data Index: 4841836 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4385. Min Range: -5.4385
Max Act: 5.0010. Min Act: -0.1700
Data Index: 981432 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4385. Min Range: -5.4385
Max Act: 5.0323. Min Act: -0.1700
Data Index: 7134984 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4385. Min Range: -5.4385
Max Act: 5.0323. Min Act: -0.1700
Data Index: 909110 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19