Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1588 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4742. Min Range: -6.4742
Max Act: 6.4742. Min Act: -0.1700
Data Index: 7096086 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4742. Min Range: -6.4742
Max Act: 6.4430. Min Act: -0.1700
Data Index: 4797584 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4742. Min Range: -6.4742
Max Act: 6.3492. Min Act: -0.1700
Data Index: 305189 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4742. Min Range: -6.4742
Max Act: 6.3180. Min Act: -0.1700
Data Index: 8395689 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4742. Min Range: -6.4742
Max Act: 6.2555. Min Act: -0.1700
Data Index: 6144833 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4742. Min Range: -6.4742
Max Act: 6.2555. Min Act: -0.1700
Data Index: 5715771 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4742. Min Range: -6.4742
Max Act: 6.2555. Min Act: -0.1700
Data Index: 4036272 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4742. Min Range: -6.4742
Max Act: 6.2242. Min Act: -0.1700
Data Index: 4444809 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4742. Min Range: -6.4742
Max Act: 6.2242. Min Act: -0.1700
Data Index: 4847575 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4742. Min Range: -6.4742
Max Act: 6.2555. Min Act: -0.1700
Data Index: 2046561 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4742. Min Range: -6.4742
Max Act: 6.2242. Min Act: -0.1700
Data Index: 6587982 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4742. Min Range: -6.4742
Max Act: 6.1930. Min Act: -0.1700
Data Index: 8508333 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4742. Min Range: -6.4742
Max Act: 6.2555. Min Act: -0.1700
Data Index: 2599574 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4742. Min Range: -6.4742
Max Act: 6.2242. Min Act: -0.1700
Data Index: 4213541 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4742. Min Range: -6.4742
Max Act: 6.1930. Min Act: -0.1700
Data Index: 1589737 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4742. Min Range: -6.4742
Max Act: 6.1930. Min Act: -0.1700
Data Index: 224666 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4742. Min Range: -6.4742
Max Act: 6.1617. Min Act: -0.1700
Data Index: 543361 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4742. Min Range: -6.4742
Max Act: 6.1617. Min Act: -0.1700
Data Index: 4970146 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4742. Min Range: -6.4742
Max Act: 6.1617. Min Act: -0.1700
Data Index: 8828107 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4742. Min Range: -6.4742
Max Act: 6.1617. Min Act: -0.1700
Data Index: 2339206 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19