Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3384 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1286. Min Range: -7.1286
Max Act: 7.1286. Min Act: -0.1700
Data Index: 5957519 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1286. Min Range: -7.1286
Max Act: 7.0661. Min Act: -0.1700
Data Index: 1217531 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1286. Min Range: -7.1286
Max Act: 6.8473. Min Act: -0.1700
Data Index: 468732 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1286. Min Range: -7.1286
Max Act: 6.7536. Min Act: -0.1700
Data Index: 7763228 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1286. Min Range: -7.1286
Max Act: 6.7223. Min Act: -0.1700
Data Index: 6689787 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1286. Min Range: -7.1286
Max Act: 6.7536. Min Act: -0.1700
Data Index: 7672025 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1286. Min Range: -7.1286
Max Act: 6.7223. Min Act: -0.1700
Data Index: 741408 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1286. Min Range: -7.1286
Max Act: 6.6911. Min Act: -0.1700
Data Index: 5558802 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1286. Min Range: -7.1286
Max Act: 6.6598. Min Act: -0.1700
Data Index: 6699003 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1286. Min Range: -7.1286
Max Act: 6.6286. Min Act: -0.1700
Data Index: 5293001 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1286. Min Range: -7.1286
Max Act: 6.6598. Min Act: -0.1700
Data Index: 6472993 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1286. Min Range: -7.1286
Max Act: 6.6286. Min Act: -0.1700
Data Index: 4174625 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1286. Min Range: -7.1286
Max Act: 6.5973. Min Act: -0.1700
Data Index: 6534463 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1286. Min Range: -7.1286
Max Act: 6.5661. Min Act: -0.1700
Data Index: 1986032 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1286. Min Range: -7.1286
Max Act: 6.5973. Min Act: -0.1700
Data Index: 3266954 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1286. Min Range: -7.1286
Max Act: 6.5661. Min Act: -0.1700
Data Index: 2609953 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1286. Min Range: -7.1286
Max Act: 6.5348. Min Act: -0.1700
Data Index: 7916158 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1286. Min Range: -7.1286
Max Act: 6.5348. Min Act: -0.1700
Data Index: 8569 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1286. Min Range: -7.1286
Max Act: 6.5036. Min Act: -0.1700
Data Index: 4247760 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1286. Min Range: -7.1286
Max Act: 6.4723. Min Act: -0.1700
Data Index: 514043 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #19