Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 138 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4655. Min Range: -6.4655
Max Act: 6.4655. Min Act: -0.1700
Data Index: 2140937 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4655. Min Range: -6.4655
Max Act: 6.4030. Min Act: -0.1700
Data Index: 504427 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4655. Min Range: -6.4655
Max Act: 6.2155. Min Act: -0.1700
Data Index: 8496799 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4655. Min Range: -6.4655
Max Act: 5.9030. Min Act: -0.1700
Data Index: 5331400 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4655. Min Range: -6.4655
Max Act: 5.8092. Min Act: -0.1700
Data Index: 266773 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4655. Min Range: -6.4655
Max Act: 5.7467. Min Act: -0.1700
Data Index: 1548633 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4655. Min Range: -6.4655
Max Act: 5.6842. Min Act: -0.1700
Data Index: 1343586 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4655. Min Range: -6.4655
Max Act: 5.6842. Min Act: -0.1700
Data Index: 8750132 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4655. Min Range: -6.4655
Max Act: 5.6842. Min Act: -0.1700
Data Index: 5425793 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4655. Min Range: -6.4655
Max Act: 5.6842. Min Act: -0.1700
Data Index: 7216044 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4655. Min Range: -6.4655
Max Act: 5.7155. Min Act: -0.1700
Data Index: 4298936 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4655. Min Range: -6.4655
Max Act: 5.5905. Min Act: -0.1700
Data Index: 1787630 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4655. Min Range: -6.4655
Max Act: 5.6530. Min Act: -0.1700
Data Index: 5965610 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4655. Min Range: -6.4655
Max Act: 5.6217. Min Act: -0.1700
Data Index: 8182659 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4655. Min Range: -6.4655
Max Act: 5.6217. Min Act: -0.1700
Data Index: 6744194 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4655. Min Range: -6.4655
Max Act: 5.5905. Min Act: -0.1700
Data Index: 5910935 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4655. Min Range: -6.4655
Max Act: 5.6217. Min Act: -0.1700
Data Index: 5545730 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4655. Min Range: -6.4655
Max Act: 5.5280. Min Act: -0.1700
Data Index: 6400705 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4655. Min Range: -6.4655
Max Act: 5.5592. Min Act: -0.1700
Data Index: 786975 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4655. Min Range: -6.4655
Max Act: 5.5592. Min Act: -0.1700
Data Index: 6996406 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19