Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 80 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.6993. Min Act: -0.1700
Data Index: 190042 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.5708. Min Act: -0.1700
Data Index: 6480273 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.5708. Min Act: -0.1700
Data Index: 8690020 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.5224. Min Act: -0.1700
Data Index: 6227133 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.5224. Min Act: -0.1700
Data Index: 691980 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.4412. Min Act: -0.1700
Data Index: 8777838 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.4412. Min Act: -0.1700
Data Index: 3616047 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.4087. Min Act: -0.1700
Data Index: 4810224 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.4087. Min Act: -0.1700
Data Index: 3073875 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.4087. Min Act: -0.1700
Data Index: 2866564 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.3923. Min Act: -0.1700
Data Index: 4218219 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.3760. Min Act: -0.1700
Data Index: 2272908 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.3760. Min Act: -0.1700
Data Index: 6267926 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.3760. Min Act: -0.1700
Data Index: 5832626 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.3596. Min Act: -0.1700
Data Index: 5742033 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.3596. Min Act: -0.1700
Data Index: 3238805 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.3596. Min Act: -0.1700
Data Index: 2480640 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.3433. Min Act: -0.1700
Data Index: 1738148 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.3269. Min Act: -0.1700
Data Index: 2882229 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6993. Min Range: -2.6993
Max Act: 2.3433. Min Act: -0.1700
Data Index: 4474832 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19