Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 486 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7772. Min Range: -5.7772
Max Act: 5.7772. Min Act: -0.1700
Data Index: 7053423 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7772. Min Range: -5.7772
Max Act: 5.3397. Min Act: -0.1700
Data Index: 8552452 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7772. Min Range: -5.7772
Max Act: 5.2772. Min Act: -0.1700
Data Index: 4462976 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7772. Min Range: -5.7772
Max Act: 5.2459. Min Act: -0.1700
Data Index: 3672788 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7772. Min Range: -5.7772
Max Act: 5.1209. Min Act: -0.1700
Data Index: 6002678 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7772. Min Range: -5.7772
Max Act: 5.1209. Min Act: -0.1700
Data Index: 7414729 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7772. Min Range: -5.7772
Max Act: 5.0897. Min Act: -0.1700
Data Index: 7374323 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7772. Min Range: -5.7772
Max Act: 5.0584. Min Act: -0.1700
Data Index: 7273671 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7772. Min Range: -5.7772
Max Act: 5.0272. Min Act: -0.1700
Data Index: 3529894 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7772. Min Range: -5.7772
Max Act: 4.9959. Min Act: -0.1700
Data Index: 6622977 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7772. Min Range: -5.7772
Max Act: 4.9647. Min Act: -0.1700
Data Index: 7328230 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7772. Min Range: -5.7772
Max Act: 4.9647. Min Act: -0.1700
Data Index: 8156696 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7772. Min Range: -5.7772
Max Act: 4.9334. Min Act: -0.1700
Data Index: 5214111 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7772. Min Range: -5.7772
Max Act: 4.9022. Min Act: -0.1700
Data Index: 6763075 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7772. Min Range: -5.7772
Max Act: 4.9334. Min Act: -0.1700
Data Index: 6763074 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7772. Min Range: -5.7772
Max Act: 4.8397. Min Act: -0.1700
Data Index: 1593378 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7772. Min Range: -5.7772
Max Act: 4.8397. Min Act: -0.1700
Data Index: 8552456 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7772. Min Range: -5.7772
Max Act: 4.8397. Min Act: -0.1700
Data Index: 7867495 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7772. Min Range: -5.7772
Max Act: 4.8084. Min Act: -0.1700
Data Index: 7414730 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7772. Min Range: -5.7772
Max Act: 4.8084. Min Act: -0.1700
Data Index: 1478761 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19