Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4082 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9093. Min Range: -1.9093
Max Act: 1.9093. Min Act: -0.1634
Data Index: 4647415 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9093. Min Range: -1.9093
Max Act: 1.8751. Min Act: -0.1700
Data Index: 96732 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9093. Min Range: -1.9093
Max Act: 1.8409. Min Act: -0.1699
Data Index: 4704346 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9093. Min Range: -1.9093
Max Act: 1.8237. Min Act: -0.1700
Data Index: 1348447 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9093. Min Range: -1.9093
Max Act: 1.8237. Min Act: -0.1700
Data Index: 2536007 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9093. Min Range: -1.9093
Max Act: 1.8237. Min Act: -0.1697
Data Index: 8556608 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9093. Min Range: -1.9093
Max Act: 1.8151. Min Act: -0.1679
Data Index: 4237022 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9093. Min Range: -1.9093
Max Act: 1.8151. Min Act: -0.1700
Data Index: 3657397 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9093. Min Range: -1.9093
Max Act: 1.8065. Min Act: -0.1699
Data Index: 7693386 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9093. Min Range: -1.9093
Max Act: 1.8065. Min Act: -0.1617
Data Index: 8331247 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9093. Min Range: -1.9093
Max Act: 1.7979. Min Act: -0.1700
Data Index: 1065979 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9093. Min Range: -1.9093
Max Act: 1.7893. Min Act: -0.1700
Data Index: 7253545 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9093. Min Range: -1.9093
Max Act: 1.7893. Min Act: -0.1700
Data Index: 3424805 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9093. Min Range: -1.9093
Max Act: 1.7979. Min Act: -0.1694
Data Index: 461667 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9093. Min Range: -1.9093
Max Act: 1.7979. Min Act: -0.1700
Data Index: 6379496 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9093. Min Range: -1.9093
Max Act: 1.7893. Min Act: -0.1699
Data Index: 5518981 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9093. Min Range: -1.9093
Max Act: 1.7893. Min Act: -0.1694
Data Index: 2918854 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9093. Min Range: -1.9093
Max Act: 1.7807. Min Act: -0.1680
Data Index: 3799770 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9093. Min Range: -1.9093
Max Act: 1.7807. Min Act: -0.1700
Data Index: 3721524 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9093. Min Range: -1.9093
Max Act: 1.7635. Min Act: -0.1699
Data Index: 2237259 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19