Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5443 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3472. Min Range: -6.3472
Max Act: 6.3472. Min Act: -0.1700
Data Index: 3906794 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3472. Min Range: -6.3472
Max Act: 6.3159. Min Act: -0.1700
Data Index: 1793197 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3472. Min Range: -6.3472
Max Act: 6.2534. Min Act: -0.1700
Data Index: 900131 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3472. Min Range: -6.3472
Max Act: 6.2534. Min Act: -0.1700
Data Index: 3240637 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3472. Min Range: -6.3472
Max Act: 6.1597. Min Act: -0.1700
Data Index: 7249581 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3472. Min Range: -6.3472
Max Act: 6.1284. Min Act: -0.1700
Data Index: 741068 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3472. Min Range: -6.3472
Max Act: 6.0972. Min Act: -0.1700
Data Index: 4019187 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3472. Min Range: -6.3472
Max Act: 6.0347. Min Act: -0.1700
Data Index: 4019188 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3472. Min Range: -6.3472
Max Act: 6.0034. Min Act: -0.1700
Data Index: 7846415 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3472. Min Range: -6.3472
Max Act: 6.0034. Min Act: -0.1700
Data Index: 4282453 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3472. Min Range: -6.3472
Max Act: 5.9722. Min Act: -0.1700
Data Index: 3438931 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3472. Min Range: -6.3472
Max Act: 5.9409. Min Act: -0.1700
Data Index: 875092 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3472. Min Range: -6.3472
Max Act: 5.9097. Min Act: -0.1700
Data Index: 3844625 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3472. Min Range: -6.3472
Max Act: 5.9097. Min Act: -0.1700
Data Index: 2933359 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3472. Min Range: -6.3472
Max Act: 5.8784. Min Act: -0.1700
Data Index: 8463880 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3472. Min Range: -6.3472
Max Act: 5.9097. Min Act: -0.1700
Data Index: 4019184 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3472. Min Range: -6.3472
Max Act: 5.8784. Min Act: -0.1700
Data Index: 3124880 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3472. Min Range: -6.3472
Max Act: 5.8784. Min Act: -0.1700
Data Index: 6564477 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3472. Min Range: -6.3472
Max Act: 5.8784. Min Act: -0.1700
Data Index: 5724532 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3472. Min Range: -6.3472
Max Act: 5.8784. Min Act: -0.1700
Data Index: 2619259 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19