Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1228 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7072. Min Range: -5.7072
Max Act: 5.7072. Min Act: -0.1700
Data Index: 5264738 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7072. Min Range: -5.7072
Max Act: 5.6447. Min Act: -0.1700
Data Index: 7826122 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7072. Min Range: -5.7072
Max Act: 5.5510. Min Act: -0.1700
Data Index: 4243334 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7072. Min Range: -5.7072
Max Act: 5.4572. Min Act: -0.1700
Data Index: 3643894 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7072. Min Range: -5.7072
Max Act: 5.4572. Min Act: -0.1700
Data Index: 5191831 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7072. Min Range: -5.7072
Max Act: 5.3635. Min Act: -0.1700
Data Index: 1514382 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7072. Min Range: -5.7072
Max Act: 5.3322. Min Act: -0.1700
Data Index: 5589870 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7072. Min Range: -5.7072
Max Act: 5.3010. Min Act: -0.1700
Data Index: 5236232 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7072. Min Range: -5.7072
Max Act: 5.3010. Min Act: -0.1700
Data Index: 7281627 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7072. Min Range: -5.7072
Max Act: 5.3010. Min Act: -0.1700
Data Index: 6767023 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7072. Min Range: -5.7072
Max Act: 5.2697. Min Act: -0.1700
Data Index: 960556 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7072. Min Range: -5.7072
Max Act: 5.2385. Min Act: -0.1700
Data Index: 798302 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7072. Min Range: -5.7072
Max Act: 5.2385. Min Act: -0.1700
Data Index: 4281647 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7072. Min Range: -5.7072
Max Act: 5.2072. Min Act: -0.1700
Data Index: 3014959 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7072. Min Range: -5.7072
Max Act: 5.2072. Min Act: -0.1700
Data Index: 6424554 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7072. Min Range: -5.7072
Max Act: 5.1760. Min Act: -0.1700
Data Index: 6693053 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7072. Min Range: -5.7072
Max Act: 5.1760. Min Act: -0.1700
Data Index: 6058825 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7072. Min Range: -5.7072
Max Act: 5.1760. Min Act: -0.1700
Data Index: 5877443 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7072. Min Range: -5.7072
Max Act: 5.1447. Min Act: -0.1700
Data Index: 42161 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7072. Min Range: -5.7072
Max Act: 5.1447. Min Act: -0.1700
Data Index: 3568014 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19