Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 636 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.8207. Min Act: -0.1700
Data Index: 1556829 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.8207. Min Act: -0.1700
Data Index: 3557918 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.7581. Min Act: -0.1700
Data Index: 456891 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.7425. Min Act: -0.1700
Data Index: 3902890 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.7268. Min Act: -0.1700
Data Index: 4703548 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.7268. Min Act: -0.1700
Data Index: 3127485 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.7268. Min Act: -0.1700
Data Index: 7372968 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.7112. Min Act: -0.1700
Data Index: 5816576 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.7112. Min Act: -0.1700
Data Index: 4774559 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.7268. Min Act: -0.1700
Data Index: 4427959 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.6956. Min Act: -0.1700
Data Index: 5735670 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.6956. Min Act: -0.1700
Data Index: 7221795 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.6956. Min Act: -0.1700
Data Index: 2898442 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.6799. Min Act: -0.1700
Data Index: 8377805 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.6799. Min Act: -0.1700
Data Index: 1395252 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.6956. Min Act: -0.1700
Data Index: 4168886 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.6643. Min Act: -0.1700
Data Index: 4999218 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.6643. Min Act: -0.1700
Data Index: 8521111 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.6643. Min Act: -0.1700
Data Index: 6846213 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8207. Min Range: -3.8207
Max Act: 3.6486. Min Act: -0.1700
Data Index: 5031881 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19