Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3165 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3256. Min Range: -7.3256
Max Act: 7.3256. Min Act: -0.1700
Data Index: 465343 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3256. Min Range: -7.3256
Max Act: 7.2006. Min Act: -0.1700
Data Index: 3555568 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3256. Min Range: -7.3256
Max Act: 7.1694. Min Act: -0.1700
Data Index: 8241748 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3256. Min Range: -7.3256
Max Act: 7.1069. Min Act: -0.1700
Data Index: 8556207 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3256. Min Range: -7.3256
Max Act: 7.1069. Min Act: -0.1700
Data Index: 8473432 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3256. Min Range: -7.3256
Max Act: 7.1069. Min Act: -0.1700
Data Index: 452796 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3256. Min Range: -7.3256
Max Act: 6.9506. Min Act: -0.1700
Data Index: 7894935 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3256. Min Range: -7.3256
Max Act: 6.8881. Min Act: -0.1700
Data Index: 7077819 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3256. Min Range: -7.3256
Max Act: 6.8256. Min Act: -0.1700
Data Index: 1114426 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3256. Min Range: -7.3256
Max Act: 6.8256. Min Act: -0.1700
Data Index: 3350160 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3256. Min Range: -7.3256
Max Act: 6.8256. Min Act: -0.1700
Data Index: 204789 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3256. Min Range: -7.3256
Max Act: 6.7631. Min Act: -0.1700
Data Index: 4479853 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3256. Min Range: -7.3256
Max Act: 6.7631. Min Act: -0.1700
Data Index: 2451213 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3256. Min Range: -7.3256
Max Act: 6.7631. Min Act: -0.1700
Data Index: 1846180 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3256. Min Range: -7.3256
Max Act: 6.7319. Min Act: -0.1700
Data Index: 5058100 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3256. Min Range: -7.3256
Max Act: 6.7319. Min Act: -0.1700
Data Index: 3671318 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3256. Min Range: -7.3256
Max Act: 6.7319. Min Act: -0.1700
Data Index: 5282582 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3256. Min Range: -7.3256
Max Act: 6.7006. Min Act: -0.1700
Data Index: 2845460 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3256. Min Range: -7.3256
Max Act: 6.7006. Min Act: -0.1700
Data Index: 8486283 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3256. Min Range: -7.3256
Max Act: 6.6694. Min Act: -0.1700
Data Index: 3855474 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19