Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1441 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.8980. Min Act: -0.1700
Data Index: 3259512 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.8667. Min Act: -0.1700
Data Index: 2336428 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.8355. Min Act: -0.1700
Data Index: 5684612 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.8042. Min Act: -0.1700
Data Index: 2476674 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.7730. Min Act: -0.1700
Data Index: 1470901 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.8042. Min Act: -0.1700
Data Index: 4737670 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.7417. Min Act: -0.1700
Data Index: 2451394 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.7105. Min Act: -0.1700
Data Index: 3811537 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.6792. Min Act: -0.1700
Data Index: 2680482 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.7105. Min Act: -0.1700
Data Index: 5621651 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.7105. Min Act: -0.1700
Data Index: 7264812 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.6792. Min Act: -0.1700
Data Index: 1482835 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.6792. Min Act: -0.1700
Data Index: 3101275 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.6792. Min Act: -0.1700
Data Index: 6947078 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.6792. Min Act: -0.1700
Data Index: 3201797 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.6480. Min Act: -0.1700
Data Index: 4915675 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.6480. Min Act: -0.1700
Data Index: 2065700 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.6480. Min Act: -0.1700
Data Index: 2817717 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.7105. Min Act: -0.1700
Data Index: 1476855 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.5855. Min Act: -0.1700
Data Index: 5853713 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19