Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5650 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7406. Min Range: -6.7406
Max Act: 6.7406. Min Act: -0.1700
Data Index: 2618719 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7406. Min Range: -6.7406
Max Act: 6.4593. Min Act: -0.1700
Data Index: 7184850 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7406. Min Range: -6.7406
Max Act: 6.3656. Min Act: -0.1700
Data Index: 6982746 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7406. Min Range: -6.7406
Max Act: 6.3343. Min Act: -0.1700
Data Index: 8701171 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7406. Min Range: -6.7406
Max Act: 6.3031. Min Act: -0.1700
Data Index: 2754499 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7406. Min Range: -6.7406
Max Act: 6.3031. Min Act: -0.1700
Data Index: 6144728 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7406. Min Range: -6.7406
Max Act: 6.2406. Min Act: -0.1700
Data Index: 5793307 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7406. Min Range: -6.7406
Max Act: 6.2093. Min Act: -0.1700
Data Index: 725207 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7406. Min Range: -6.7406
Max Act: 6.1468. Min Act: -0.1700
Data Index: 5453576 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7406. Min Range: -6.7406
Max Act: 6.1468. Min Act: -0.1700
Data Index: 5149385 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7406. Min Range: -6.7406
Max Act: 6.1468. Min Act: -0.1700
Data Index: 2494611 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7406. Min Range: -6.7406
Max Act: 6.1156. Min Act: -0.1700
Data Index: 5378607 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7406. Min Range: -6.7406
Max Act: 6.1156. Min Act: -0.1700
Data Index: 5670643 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7406. Min Range: -6.7406
Max Act: 6.0843. Min Act: -0.1700
Data Index: 84514 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7406. Min Range: -6.7406
Max Act: 6.0843. Min Act: -0.1700
Data Index: 106243 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7406. Min Range: -6.7406
Max Act: 6.0531. Min Act: -0.1700
Data Index: 1645783 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7406. Min Range: -6.7406
Max Act: 6.0843. Min Act: -0.1700
Data Index: 4414827 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7406. Min Range: -6.7406
Max Act: 6.0843. Min Act: -0.1700
Data Index: 2137724 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7406. Min Range: -6.7406
Max Act: 5.9906. Min Act: -0.1700
Data Index: 6814381 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7406. Min Range: -6.7406
Max Act: 5.9593. Min Act: -0.1700
Data Index: 4363157 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19