Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4106 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3205. Min Range: -7.3205
Max Act: 7.3205. Min Act: -0.1700
Data Index: 5415599 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3205. Min Range: -7.3205
Max Act: 7.2267. Min Act: -0.1700
Data Index: 5937735 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3205. Min Range: -7.3205
Max Act: 7.2267. Min Act: -0.1700
Data Index: 3549843 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3205. Min Range: -7.3205
Max Act: 7.1330. Min Act: -0.1700
Data Index: 4986790 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3205. Min Range: -7.3205
Max Act: 7.1017. Min Act: -0.1700
Data Index: 3573914 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3205. Min Range: -7.3205
Max Act: 7.0080. Min Act: -0.1700
Data Index: 2637306 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3205. Min Range: -7.3205
Max Act: 6.9767. Min Act: -0.1700
Data Index: 6007147 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3205. Min Range: -7.3205
Max Act: 6.9767. Min Act: -0.1700
Data Index: 700578 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3205. Min Range: -7.3205
Max Act: 6.9142. Min Act: -0.1700
Data Index: 1877832 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3205. Min Range: -7.3205
Max Act: 6.9142. Min Act: -0.1700
Data Index: 3484918 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3205. Min Range: -7.3205
Max Act: 6.9767. Min Act: -0.1700
Data Index: 8295568 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3205. Min Range: -7.3205
Max Act: 6.8830. Min Act: -0.1700
Data Index: 1568930 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3205. Min Range: -7.3205
Max Act: 6.9142. Min Act: -0.1700
Data Index: 89748 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3205. Min Range: -7.3205
Max Act: 6.8830. Min Act: -0.1700
Data Index: 4444624 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3205. Min Range: -7.3205
Max Act: 6.8830. Min Act: -0.1700
Data Index: 7749272 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3205. Min Range: -7.3205
Max Act: 6.8830. Min Act: -0.1700
Data Index: 1815321 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3205. Min Range: -7.3205
Max Act: 6.8830. Min Act: -0.1700
Data Index: 8416589 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3205. Min Range: -7.3205
Max Act: 6.8517. Min Act: -0.1700
Data Index: 6612483 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3205. Min Range: -7.3205
Max Act: 6.8517. Min Act: -0.1700
Data Index: 3734307 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3205. Min Range: -7.3205
Max Act: 6.8205. Min Act: -0.1700
Data Index: 1739333 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #19