Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2534 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9899. Min Range: -5.9899
Max Act: 5.9586. Min Act: -0.1700
Data Index: 3131079 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9899. Min Range: -5.9899
Max Act: 5.9899. Min Act: -0.1700
Data Index: 6922971 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9899. Min Range: -5.9899
Max Act: 5.9586. Min Act: -0.1700
Data Index: 2229166 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9899. Min Range: -5.9899
Max Act: 5.9586. Min Act: -0.1700
Data Index: 3995061 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9899. Min Range: -5.9899
Max Act: 5.9274. Min Act: -0.1700
Data Index: 5540364 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9899. Min Range: -5.9899
Max Act: 5.8649. Min Act: -0.1700
Data Index: 8242324 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9899. Min Range: -5.9899
Max Act: 5.8961. Min Act: -0.1700
Data Index: 8242323 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9899. Min Range: -5.9899
Max Act: 5.8024. Min Act: -0.1700
Data Index: 3780716 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9899. Min Range: -5.9899
Max Act: 5.7711. Min Act: -0.1700
Data Index: 368986 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9899. Min Range: -5.9899
Max Act: 5.7711. Min Act: -0.1700
Data Index: 6797540 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9899. Min Range: -5.9899
Max Act: 5.7086. Min Act: -0.1700
Data Index: 5540362 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9899. Min Range: -5.9899
Max Act: 5.6461. Min Act: -0.1700
Data Index: 4118411 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9899. Min Range: -5.9899
Max Act: 5.6461. Min Act: -0.1700
Data Index: 7395385 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9899. Min Range: -5.9899
Max Act: 5.6774. Min Act: -0.1700
Data Index: 3969267 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9899. Min Range: -5.9899
Max Act: 5.5836. Min Act: -0.1700
Data Index: 7395387 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9899. Min Range: -5.9899
Max Act: 5.5836. Min Act: -0.1700
Data Index: 8242325 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9899. Min Range: -5.9899
Max Act: 5.5524. Min Act: -0.1700
Data Index: 4667926 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9899. Min Range: -5.9899
Max Act: 5.5524. Min Act: -0.1700
Data Index: 8491728 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9899. Min Range: -5.9899
Max Act: 5.5524. Min Act: -0.1700
Data Index: 4314021 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9899. Min Range: -5.9899
Max Act: 5.5211. Min Act: -0.1700
Data Index: 4703704 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #19