Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3012 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0423. Min Range: -6.0423
Max Act: 6.0423. Min Act: -0.1700
Data Index: 3201471 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0423. Min Range: -6.0423
Max Act: 5.8861. Min Act: -0.1700
Data Index: 1080555 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0423. Min Range: -6.0423
Max Act: 5.8861. Min Act: -0.1700
Data Index: 3160446 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0423. Min Range: -6.0423
Max Act: 5.8548. Min Act: -0.1700
Data Index: 3700554 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0423. Min Range: -6.0423
Max Act: 5.8236. Min Act: -0.1700
Data Index: 4125839 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0423. Min Range: -6.0423
Max Act: 5.6986. Min Act: -0.1700
Data Index: 1372585 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0423. Min Range: -6.0423
Max Act: 5.7298. Min Act: -0.1700
Data Index: 3259037 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0423. Min Range: -6.0423
Max Act: 5.6986. Min Act: -0.1700
Data Index: 411686 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0423. Min Range: -6.0423
Max Act: 5.6986. Min Act: -0.1700
Data Index: 2462050 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0423. Min Range: -6.0423
Max Act: 5.6986. Min Act: -0.1700
Data Index: 719820 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0423. Min Range: -6.0423
Max Act: 5.6986. Min Act: -0.1700
Data Index: 246221 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0423. Min Range: -6.0423
Max Act: 5.6673. Min Act: -0.1700
Data Index: 8509840 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0423. Min Range: -6.0423
Max Act: 5.6361. Min Act: -0.1700
Data Index: 1997485 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0423. Min Range: -6.0423
Max Act: 5.6361. Min Act: -0.1700
Data Index: 1450067 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0423. Min Range: -6.0423
Max Act: 5.6361. Min Act: -0.1700
Data Index: 592962 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0423. Min Range: -6.0423
Max Act: 5.6361. Min Act: -0.1700
Data Index: 60840 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0423. Min Range: -6.0423
Max Act: 5.6361. Min Act: -0.1700
Data Index: 5587283 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0423. Min Range: -6.0423
Max Act: 5.6361. Min Act: -0.1700
Data Index: 4159633 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0423. Min Range: -6.0423
Max Act: 5.6048. Min Act: -0.1700
Data Index: 438282 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0423. Min Range: -6.0423
Max Act: 5.6048. Min Act: -0.1700
Data Index: 3781359 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19