Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2995 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.6695. Min Act: -0.1700
Data Index: 8010093 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.3882. Min Act: -0.1700
Data Index: 2597267 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.3570. Min Act: -0.1700
Data Index: 7480875 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.3257. Min Act: -0.1700
Data Index: 5822171 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.2945. Min Act: -0.1700
Data Index: 1716247 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.2945. Min Act: -0.1700
Data Index: 2417549 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.2945. Min Act: -0.1700
Data Index: 8340944 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.2632. Min Act: -0.1700
Data Index: 7439724 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.2632. Min Act: -0.1700
Data Index: 1584131 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.2320. Min Act: -0.1700
Data Index: 5292183 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.2320. Min Act: -0.1700
Data Index: 1630753 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.2320. Min Act: -0.1700
Data Index: 1011092 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.2007. Min Act: -0.1700
Data Index: 1809178 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.2007. Min Act: -0.1700
Data Index: 4497238 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.1695. Min Act: -0.1700
Data Index: 3243701 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.1695. Min Act: -0.1700
Data Index: 591227 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.2007. Min Act: -0.1700
Data Index: 5873276 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.1695. Min Act: -0.1700
Data Index: 3886384 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.1695. Min Act: -0.1700
Data Index: 4425688 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6695. Min Range: -6.6695
Max Act: 6.1695. Min Act: -0.1700
Data Index: 5536444 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19