Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1122 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4271. Min Range: -5.4271
Max Act: 5.4271. Min Act: -0.1700
Data Index: 3296418 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4271. Min Range: -5.4271
Max Act: 5.3333. Min Act: -0.1700
Data Index: 1201049 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4271. Min Range: -5.4271
Max Act: 5.2083. Min Act: -0.1700
Data Index: 8799714 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4271. Min Range: -5.4271
Max Act: 5.1458. Min Act: -0.1700
Data Index: 5300344 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4271. Min Range: -5.4271
Max Act: 5.0833. Min Act: -0.1700
Data Index: 8208523 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4271. Min Range: -5.4271
Max Act: 5.0833. Min Act: -0.1700
Data Index: 5618365 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4271. Min Range: -5.4271
Max Act: 5.0208. Min Act: -0.1700
Data Index: 2252137 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4271. Min Range: -5.4271
Max Act: 5.0833. Min Act: -0.1700
Data Index: 6865471 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4271. Min Range: -5.4271
Max Act: 5.0208. Min Act: -0.1700
Data Index: 7646791 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4271. Min Range: -5.4271
Max Act: 5.0208. Min Act: -0.1700
Data Index: 177320 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4271. Min Range: -5.4271
Max Act: 5.0208. Min Act: -0.1700
Data Index: 6711269 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4271. Min Range: -5.4271
Max Act: 4.9896. Min Act: -0.1700
Data Index: 2214531 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4271. Min Range: -5.4271
Max Act: 4.9896. Min Act: -0.1700
Data Index: 5663394 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4271. Min Range: -5.4271
Max Act: 4.9896. Min Act: -0.1700
Data Index: 2452656 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4271. Min Range: -5.4271
Max Act: 4.9896. Min Act: -0.1700
Data Index: 1570886 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4271. Min Range: -5.4271
Max Act: 4.9583. Min Act: -0.1700
Data Index: 499477 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4271. Min Range: -5.4271
Max Act: 4.9583. Min Act: -0.1700
Data Index: 4366502 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4271. Min Range: -5.4271
Max Act: 4.9583. Min Act: -0.1700
Data Index: 499474 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4271. Min Range: -5.4271
Max Act: 4.9583. Min Act: -0.1700
Data Index: 499476 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4271. Min Range: -5.4271
Max Act: 4.8958. Min Act: -0.1700
Data Index: 3028047 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19