Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3583 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.9996. Min Range: -7.9996
Max Act: 7.9996. Min Act: -0.1700
Data Index: 6835142 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9996. Min Range: -7.9996
Max Act: 7.9996. Min Act: -0.1700
Data Index: 5962236 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9996. Min Range: -7.9996
Max Act: 7.9059. Min Act: -0.1700
Data Index: 6517843 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9996. Min Range: -7.9996
Max Act: 7.8746. Min Act: -0.1700
Data Index: 2372358 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9996. Min Range: -7.9996
Max Act: 7.8434. Min Act: -0.1700
Data Index: 6619897 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9996. Min Range: -7.9996
Max Act: 7.6871. Min Act: -0.1700
Data Index: 2294236 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9996. Min Range: -7.9996
Max Act: 7.6559. Min Act: -0.1700
Data Index: 511623 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9996. Min Range: -7.9996
Max Act: 7.6559. Min Act: -0.1700
Data Index: 8227429 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9996. Min Range: -7.9996
Max Act: 7.5934. Min Act: -0.1700
Data Index: 3924880 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9996. Min Range: -7.9996
Max Act: 7.6246. Min Act: -0.1700
Data Index: 8533159 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9996. Min Range: -7.9996
Max Act: 7.5621. Min Act: -0.1700
Data Index: 22520 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9996. Min Range: -7.9996
Max Act: 7.5934. Min Act: -0.1700
Data Index: 4528091 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9996. Min Range: -7.9996
Max Act: 7.5934. Min Act: -0.1700
Data Index: 5342011 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9996. Min Range: -7.9996
Max Act: 7.5621. Min Act: -0.1700
Data Index: 3449921 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9996. Min Range: -7.9996
Max Act: 7.5934. Min Act: -0.1700
Data Index: 2009565 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9996. Min Range: -7.9996
Max Act: 7.5309. Min Act: -0.1700
Data Index: 8243410 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9996. Min Range: -7.9996
Max Act: 7.5934. Min Act: -0.1700
Data Index: 3136755 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9996. Min Range: -7.9996
Max Act: 7.4996. Min Act: -0.1700
Data Index: 1600212 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9996. Min Range: -7.9996
Max Act: 7.5621. Min Act: -0.1700
Data Index: 5639649 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9996. Min Range: -7.9996
Max Act: 7.5309. Min Act: -0.1700
Data Index: 388768 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19