Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 445 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.5690. Min Range: -8.5690
Max Act: 8.5690. Min Act: -0.1700
Data Index: 6887776 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5690. Min Range: -8.5690
Max Act: 8.4440. Min Act: -0.1700
Data Index: 8683814 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5690. Min Range: -8.5690
Max Act: 8.3190. Min Act: -0.1700
Data Index: 8398544 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5690. Min Range: -8.5690
Max Act: 8.3190. Min Act: -0.1700
Data Index: 4690710 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5690. Min Range: -8.5690
Max Act: 8.3190. Min Act: -0.1700
Data Index: 8801474 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5690. Min Range: -8.5690
Max Act: 8.2565. Min Act: -0.1700
Data Index: 7984615 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5690. Min Range: -8.5690
Max Act: 8.1940. Min Act: -0.1700
Data Index: 1897957 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5690. Min Range: -8.5690
Max Act: 8.2565. Min Act: -0.1700
Data Index: 1858276 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5690. Min Range: -8.5690
Max Act: 8.1940. Min Act: -0.1700
Data Index: 989803 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5690. Min Range: -8.5690
Max Act: 8.1940. Min Act: -0.1700
Data Index: 1474681 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5690. Min Range: -8.5690
Max Act: 8.1940. Min Act: -0.1700
Data Index: 1396972 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5690. Min Range: -8.5690
Max Act: 8.1940. Min Act: -0.1700
Data Index: 2416502 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5690. Min Range: -8.5690
Max Act: 8.1315. Min Act: -0.1700
Data Index: 7456394 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5690. Min Range: -8.5690
Max Act: 8.1315. Min Act: -0.1700
Data Index: 7611140 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5690. Min Range: -8.5690
Max Act: 8.1315. Min Act: -0.1700
Data Index: 6642432 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5690. Min Range: -8.5690
Max Act: 8.1315. Min Act: -0.1700
Data Index: 7777749 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5690. Min Range: -8.5690
Max Act: 8.1315. Min Act: -0.1700
Data Index: 1087456 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5690. Min Range: -8.5690
Max Act: 8.1315. Min Act: -0.1700
Data Index: 5460183 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5690. Min Range: -8.5690
Max Act: 8.1315. Min Act: -0.1700
Data Index: 4195333 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5690. Min Range: -8.5690
Max Act: 8.0690. Min Act: -0.1700
Data Index: 4746995 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19