Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 497 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0900. Min Range: -3.0900
Max Act: 3.0900. Min Act: -0.1700
Data Index: 8284916 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0900. Min Range: -3.0900
Max Act: 3.0585. Min Act: -0.1700
Data Index: 7759541 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.9953. Min Act: -0.1700
Data Index: 8759938 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0900. Min Range: -3.0900
Max Act: 3.0111. Min Act: -0.1700
Data Index: 418908 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.9953. Min Act: -0.1700
Data Index: 8019579 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.9320. Min Act: -0.1700
Data Index: 4592395 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.9320. Min Act: -0.1700
Data Index: 7417937 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.9003. Min Act: -0.1700
Data Index: 3048824 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.8844. Min Act: -0.1700
Data Index: 1636915 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.8844. Min Act: -0.1700
Data Index: 8098151 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.8686. Min Act: -0.1700
Data Index: 6156507 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.8527. Min Act: -0.1700
Data Index: 5789099 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.8368. Min Act: -0.1700
Data Index: 2976805 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.8209. Min Act: -0.1700
Data Index: 7344661 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.8209. Min Act: -0.1700
Data Index: 4999516 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.8209. Min Act: -0.1700
Data Index: 4254600 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.8050. Min Act: -0.1700
Data Index: 7365574 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.8050. Min Act: -0.1700
Data Index: 3838126 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.8050. Min Act: -0.1700
Data Index: 6025934 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0900. Min Range: -3.0900
Max Act: 2.7891. Min Act: -0.1700
Data Index: 6257418 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19