Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3470 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0497. Min Range: -6.0497
Max Act: 6.0497. Min Act: -0.1700
Data Index: 1148881 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.9560. Min Act: -0.1700
Data Index: 2314306 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.9247. Min Act: -0.1700
Data Index: 1011069 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.8622. Min Act: -0.1700
Data Index: 1483153 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.8935. Min Act: -0.1700
Data Index: 7659519 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.8622. Min Act: -0.1700
Data Index: 6630822 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.8310. Min Act: -0.1700
Data Index: 507761 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.7997. Min Act: -0.1700
Data Index: 1419477 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.7685. Min Act: -0.1700
Data Index: 7267049 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.7685. Min Act: -0.1700
Data Index: 1526530 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.7372. Min Act: -0.1700
Data Index: 1307617 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.7372. Min Act: -0.1700
Data Index: 2268600 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.7372. Min Act: -0.1700
Data Index: 3710254 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.7372. Min Act: -0.1700
Data Index: 6991597 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.7372. Min Act: -0.1700
Data Index: 6842836 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.7060. Min Act: -0.1700
Data Index: 4920100 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.7060. Min Act: -0.1700
Data Index: 5169868 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.7060. Min Act: -0.1700
Data Index: 49271 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.7060. Min Act: -0.1700
Data Index: 5257461 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0497. Min Range: -6.0497
Max Act: 5.7060. Min Act: -0.1700
Data Index: 5568009 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19