Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2578 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.6265. Min Range: -7.6265
Max Act: 7.6265. Min Act: -0.1700
Data Index: 663073 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6265. Min Range: -7.6265
Max Act: 7.4390. Min Act: -0.1700
Data Index: 4846716 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6265. Min Range: -7.6265
Max Act: 7.4077. Min Act: -0.1700
Data Index: 57614 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6265. Min Range: -7.6265
Max Act: 7.4077. Min Act: -0.1700
Data Index: 697678 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6265. Min Range: -7.6265
Max Act: 7.4077. Min Act: -0.1700
Data Index: 4025239 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6265. Min Range: -7.6265
Max Act: 7.3452. Min Act: -0.1700
Data Index: 5279969 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6265. Min Range: -7.6265
Max Act: 7.3140. Min Act: -0.1700
Data Index: 3156244 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6265. Min Range: -7.6265
Max Act: 7.3140. Min Act: -0.1700
Data Index: 8492733 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6265. Min Range: -7.6265
Max Act: 7.2827. Min Act: -0.1700
Data Index: 675471 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6265. Min Range: -7.6265
Max Act: 7.2515. Min Act: -0.1700
Data Index: 7136869 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6265. Min Range: -7.6265
Max Act: 7.2827. Min Act: -0.1700
Data Index: 1831292 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6265. Min Range: -7.6265
Max Act: 7.2515. Min Act: -0.1700
Data Index: 1393083 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6265. Min Range: -7.6265
Max Act: 7.2202. Min Act: -0.1700
Data Index: 1768764 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6265. Min Range: -7.6265
Max Act: 7.2515. Min Act: -0.1700
Data Index: 1867300 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6265. Min Range: -7.6265
Max Act: 7.2515. Min Act: -0.1700
Data Index: 2363703 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6265. Min Range: -7.6265
Max Act: 7.2202. Min Act: -0.1700
Data Index: 3943819 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6265. Min Range: -7.6265
Max Act: 7.1890. Min Act: -0.1700
Data Index: 6163417 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6265. Min Range: -7.6265
Max Act: 7.1890. Min Act: -0.1700
Data Index: 1913553 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6265. Min Range: -7.6265
Max Act: 7.1890. Min Act: -0.1700
Data Index: 6001919 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6265. Min Range: -7.6265
Max Act: 7.1577. Min Act: -0.1700
Data Index: 6420274 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19