Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1906 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3534. Min Range: -8.3534
Max Act: 8.3534. Min Act: -0.1700
Data Index: 4510934 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3534. Min Range: -8.3534
Max Act: 8.1034. Min Act: -0.1700
Data Index: 1594748 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3534. Min Range: -8.3534
Max Act: 8.0409. Min Act: -0.1700
Data Index: 4620576 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3534. Min Range: -8.3534
Max Act: 8.0409. Min Act: -0.1700
Data Index: 4451345 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3534. Min Range: -8.3534
Max Act: 7.9159. Min Act: -0.1700
Data Index: 210594 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3534. Min Range: -8.3534
Max Act: 7.8846. Min Act: -0.1700
Data Index: 2136218 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3534. Min Range: -8.3534
Max Act: 7.7596. Min Act: -0.1700
Data Index: 6619353 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3534. Min Range: -8.3534
Max Act: 7.7284. Min Act: -0.1700
Data Index: 8508367 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3534. Min Range: -8.3534
Max Act: 7.6971. Min Act: -0.1700
Data Index: 168817 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3534. Min Range: -8.3534
Max Act: 7.6971. Min Act: -0.1700
Data Index: 6639084 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3534. Min Range: -8.3534
Max Act: 7.5409. Min Act: -0.1700
Data Index: 8352713 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3534. Min Range: -8.3534
Max Act: 7.5409. Min Act: -0.1700
Data Index: 7566465 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3534. Min Range: -8.3534
Max Act: 7.5409. Min Act: -0.1700
Data Index: 5277778 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3534. Min Range: -8.3534
Max Act: 7.4784. Min Act: -0.1700
Data Index: 228310 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3534. Min Range: -8.3534
Max Act: 7.4784. Min Act: -0.1700
Data Index: 1406224 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3534. Min Range: -8.3534
Max Act: 7.4471. Min Act: -0.1700
Data Index: 3705433 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3534. Min Range: -8.3534
Max Act: 7.4159. Min Act: -0.1700
Data Index: 7402821 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3534. Min Range: -8.3534
Max Act: 7.4159. Min Act: -0.1700
Data Index: 138815 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3534. Min Range: -8.3534
Max Act: 7.3846. Min Act: -0.1700
Data Index: 1319201 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3534. Min Range: -8.3534
Max Act: 7.3846. Min Act: -0.1700
Data Index: 6763464 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19