Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1056 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8190. Min Range: -2.8190
Max Act: 2.8190. Min Act: -0.1700
Data Index: 5687849 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8190. Min Range: -2.8190
Max Act: 2.7871. Min Act: -0.1700
Data Index: 4007714 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8190. Min Range: -2.8190
Max Act: 2.7393. Min Act: -0.1700
Data Index: 4565412 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8190. Min Range: -2.8190
Max Act: 2.7233. Min Act: -0.1700
Data Index: 3742096 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8190. Min Range: -2.8190
Max Act: 2.7393. Min Act: -0.1700
Data Index: 623324 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8190. Min Range: -2.8190
Max Act: 2.7073. Min Act: -0.1700
Data Index: 1001061 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8190. Min Range: -2.8190
Max Act: 2.6913. Min Act: -0.1700
Data Index: 8378929 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8190. Min Range: -2.8190
Max Act: 2.6913. Min Act: -0.1700
Data Index: 5908944 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8190. Min Range: -2.8190
Max Act: 2.7073. Min Act: -0.1700
Data Index: 4453197 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8190. Min Range: -2.8190
Max Act: 2.6753. Min Act: -0.1700
Data Index: 357594 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8190. Min Range: -2.8190
Max Act: 2.6753. Min Act: -0.1700
Data Index: 8708554 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8190. Min Range: -2.8190
Max Act: 2.6432. Min Act: -0.1700
Data Index: 6090378 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8190. Min Range: -2.8190
Max Act: 2.6272. Min Act: -0.1700
Data Index: 602364 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8190. Min Range: -2.8190
Max Act: 2.6272. Min Act: -0.1700
Data Index: 1022779 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8190. Min Range: -2.8190
Max Act: 2.6272. Min Act: -0.1700
Data Index: 4209557 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8190. Min Range: -2.8190
Max Act: 2.6111. Min Act: -0.1700
Data Index: 8255663 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8190. Min Range: -2.8190
Max Act: 2.5950. Min Act: -0.1700
Data Index: 6073578 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8190. Min Range: -2.8190
Max Act: 2.5950. Min Act: -0.1700
Data Index: 4458848 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8190. Min Range: -2.8190
Max Act: 2.6111. Min Act: -0.1700
Data Index: 1904230 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8190. Min Range: -2.8190
Max Act: 2.5950. Min Act: -0.1700
Data Index: 5056770 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19