Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4984 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0347. Min Range: -6.0347
Max Act: 6.0347. Min Act: -0.1700
Data Index: 3567196 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0347. Min Range: -6.0347
Max Act: 5.9722. Min Act: -0.1700
Data Index: 3881031 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0347. Min Range: -6.0347
Max Act: 5.9409. Min Act: -0.1700
Data Index: 5588277 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0347. Min Range: -6.0347
Max Act: 5.8784. Min Act: -0.1700
Data Index: 4750167 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0347. Min Range: -6.0347
Max Act: 5.7847. Min Act: -0.1700
Data Index: 220934 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0347. Min Range: -6.0347
Max Act: 5.8159. Min Act: -0.1700
Data Index: 7358677 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0347. Min Range: -6.0347
Max Act: 5.7534. Min Act: -0.1700
Data Index: 191354 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0347. Min Range: -6.0347
Max Act: 5.6909. Min Act: -0.1700
Data Index: 2800147 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0347. Min Range: -6.0347
Max Act: 5.6284. Min Act: -0.1700
Data Index: 5962172 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0347. Min Range: -6.0347
Max Act: 5.6284. Min Act: -0.1700
Data Index: 5660609 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0347. Min Range: -6.0347
Max Act: 5.6597. Min Act: -0.1700
Data Index: 7240904 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0347. Min Range: -6.0347
Max Act: 5.5659. Min Act: -0.1700
Data Index: 1760811 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0347. Min Range: -6.0347
Max Act: 5.5347. Min Act: -0.1700
Data Index: 1774282 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0347. Min Range: -6.0347
Max Act: 5.5659. Min Act: -0.1700
Data Index: 3748344 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0347. Min Range: -6.0347
Max Act: 5.5347. Min Act: -0.1700
Data Index: 4364292 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0347. Min Range: -6.0347
Max Act: 5.5347. Min Act: -0.1700
Data Index: 6100005 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0347. Min Range: -6.0347
Max Act: 5.5034. Min Act: -0.1700
Data Index: 4283428 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0347. Min Range: -6.0347
Max Act: 5.5034. Min Act: -0.1700
Data Index: 6906899 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0347. Min Range: -6.0347
Max Act: 5.5034. Min Act: -0.1700
Data Index: 2496783 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0347. Min Range: -6.0347
Max Act: 5.5034. Min Act: -0.1700
Data Index: 6303621 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19