Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3407 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0736. Min Range: -4.0736
Max Act: 4.0736. Min Act: -0.1700
Data Index: 6076357 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0736. Min Range: -4.0736
Max Act: 3.7922. Min Act: -0.1700
Data Index: 387162 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0736. Min Range: -4.0736
Max Act: 3.7922. Min Act: -0.1700
Data Index: 4916343 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0736. Min Range: -4.0736
Max Act: 3.7609. Min Act: -0.1700
Data Index: 2263504 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0736. Min Range: -4.0736
Max Act: 3.6984. Min Act: -0.1700
Data Index: 4012569 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0736. Min Range: -4.0736
Max Act: 3.6671. Min Act: -0.1700
Data Index: 389887 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0736. Min Range: -4.0736
Max Act: 3.6358. Min Act: -0.1700
Data Index: 6707315 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0736. Min Range: -4.0736
Max Act: 3.6358. Min Act: -0.1700
Data Index: 4614754 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0736. Min Range: -4.0736
Max Act: 3.6358. Min Act: -0.1700
Data Index: 8484737 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0736. Min Range: -4.0736
Max Act: 3.6358. Min Act: -0.1700
Data Index: 7750603 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0736. Min Range: -4.0736
Max Act: 3.6045. Min Act: -0.1700
Data Index: 6406055 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0736. Min Range: -4.0736
Max Act: 3.6358. Min Act: -0.1700
Data Index: 1489794 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0736. Min Range: -4.0736
Max Act: 3.6045. Min Act: -0.1700
Data Index: 7552632 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0736. Min Range: -4.0736
Max Act: 3.6045. Min Act: -0.1700
Data Index: 3081500 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0736. Min Range: -4.0736
Max Act: 3.6045. Min Act: -0.1700
Data Index: 6271694 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0736. Min Range: -4.0736
Max Act: 3.6045. Min Act: -0.1700
Data Index: 4423611 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0736. Min Range: -4.0736
Max Act: 3.6045. Min Act: -0.1700
Data Index: 7552627 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0736. Min Range: -4.0736
Max Act: 3.6045. Min Act: -0.1700
Data Index: 4367668 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0736. Min Range: -4.0736
Max Act: 3.5732. Min Act: -0.1700
Data Index: 6738691 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0736. Min Range: -4.0736
Max Act: 3.5732. Min Act: -0.1700
Data Index: 3207652 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19