Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4585 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0797. Min Range: -7.0797
Max Act: 7.0484. Min Act: -0.1700
Data Index: 4688635 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0797. Min Range: -7.0797
Max Act: 7.0484. Min Act: -0.1700
Data Index: 3050937 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0797. Min Range: -7.0797
Max Act: 7.0797. Min Act: -0.1700
Data Index: 3105564 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0797. Min Range: -7.0797
Max Act: 7.0172. Min Act: -0.1700
Data Index: 5828212 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.9547. Min Act: -0.1700
Data Index: 6512925 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.8609. Min Act: -0.1700
Data Index: 8783409 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.8297. Min Act: -0.1700
Data Index: 7336430 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.8297. Min Act: -0.1700
Data Index: 141863 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.7984. Min Act: -0.1700
Data Index: 1146576 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.7984. Min Act: -0.1700
Data Index: 654465 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.7984. Min Act: -0.1700
Data Index: 8641210 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.7672. Min Act: -0.1700
Data Index: 1713454 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.7672. Min Act: -0.1700
Data Index: 370445 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.7672. Min Act: -0.1700
Data Index: 3291788 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.7672. Min Act: -0.1700
Data Index: 45718 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.7359. Min Act: -0.1700
Data Index: 5362329 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.7359. Min Act: -0.1700
Data Index: 8457721 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.7359. Min Act: -0.1700
Data Index: 8263985 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.7359. Min Act: -0.1700
Data Index: 1191330 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0797. Min Range: -7.0797
Max Act: 6.7359. Min Act: -0.1700
Data Index: 4106806 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19