Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 855 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4467. Min Range: -8.4467
Max Act: 8.4467. Min Act: -0.1700
Data Index: 4116431 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4467. Min Range: -8.4467
Max Act: 8.4467. Min Act: -0.1700
Data Index: 8037222 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4467. Min Range: -8.4467
Max Act: 8.2592. Min Act: -0.1700
Data Index: 1234940 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4467. Min Range: -8.4467
Max Act: 8.1654. Min Act: -0.1700
Data Index: 7430394 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4467. Min Range: -8.4467
Max Act: 8.1967. Min Act: -0.1700
Data Index: 371113 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4467. Min Range: -8.4467
Max Act: 8.0717. Min Act: -0.1700
Data Index: 1787999 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4467. Min Range: -8.4467
Max Act: 8.0404. Min Act: -0.1700
Data Index: 1958840 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4467. Min Range: -8.4467
Max Act: 7.9779. Min Act: -0.1700
Data Index: 1252516 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4467. Min Range: -8.4467
Max Act: 7.9154. Min Act: -0.1700
Data Index: 7041785 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4467. Min Range: -8.4467
Max Act: 7.9467. Min Act: -0.1700
Data Index: 8770749 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4467. Min Range: -8.4467
Max Act: 7.8529. Min Act: -0.1700
Data Index: 2397824 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4467. Min Range: -8.4467
Max Act: 7.8842. Min Act: -0.1700
Data Index: 4638064 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4467. Min Range: -8.4467
Max Act: 7.9154. Min Act: -0.1700
Data Index: 7901394 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4467. Min Range: -8.4467
Max Act: 7.8529. Min Act: -0.1700
Data Index: 1348414 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4467. Min Range: -8.4467
Max Act: 7.8529. Min Act: -0.1700
Data Index: 6535530 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4467. Min Range: -8.4467
Max Act: 7.8842. Min Act: -0.1700
Data Index: 1430949 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4467. Min Range: -8.4467
Max Act: 7.8217. Min Act: -0.1700
Data Index: 8389443 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4467. Min Range: -8.4467
Max Act: 7.8217. Min Act: -0.1700
Data Index: 7465152 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4467. Min Range: -8.4467
Max Act: 7.7904. Min Act: -0.1700
Data Index: 4088499 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4467. Min Range: -8.4467
Max Act: 7.7592. Min Act: -0.1700
Data Index: 5712859 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19