Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 724 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0585. Min Range: -7.0585
Max Act: 7.0585. Min Act: -0.1700
Data Index: 504163 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0585. Min Range: -7.0585
Max Act: 6.8710. Min Act: -0.1700
Data Index: 8014791 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0585. Min Range: -7.0585
Max Act: 6.4335. Min Act: -0.1700
Data Index: 7795868 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0585. Min Range: -7.0585
Max Act: 6.3710. Min Act: -0.1700
Data Index: 2178715 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0585. Min Range: -7.0585
Max Act: 6.2460. Min Act: -0.1700
Data Index: 6120949 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0585. Min Range: -7.0585
Max Act: 6.1835. Min Act: -0.1700
Data Index: 1087856 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0585. Min Range: -7.0585
Max Act: 6.0898. Min Act: -0.1700
Data Index: 929753 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0585. Min Range: -7.0585
Max Act: 5.9960. Min Act: -0.1700
Data Index: 4869677 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0585. Min Range: -7.0585
Max Act: 5.9960. Min Act: -0.1700
Data Index: 4283464 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0585. Min Range: -7.0585
Max Act: 5.9335. Min Act: -0.1700
Data Index: 3130128 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0585. Min Range: -7.0585
Max Act: 5.9335. Min Act: -0.1700
Data Index: 3079473 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0585. Min Range: -7.0585
Max Act: 5.9335. Min Act: -0.1700
Data Index: 7588606 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0585. Min Range: -7.0585
Max Act: 5.8710. Min Act: -0.1700
Data Index: 52293 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0585. Min Range: -7.0585
Max Act: 5.8710. Min Act: -0.1700
Data Index: 2882229 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0585. Min Range: -7.0585
Max Act: 5.8398. Min Act: -0.1700
Data Index: 2532924 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0585. Min Range: -7.0585
Max Act: 5.8085. Min Act: -0.1700
Data Index: 4248111 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0585. Min Range: -7.0585
Max Act: 5.8085. Min Act: -0.1700
Data Index: 8333702 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0585. Min Range: -7.0585
Max Act: 5.7773. Min Act: -0.1700
Data Index: 1190509 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0585. Min Range: -7.0585
Max Act: 5.7773. Min Act: -0.1700
Data Index: 5488766 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0585. Min Range: -7.0585
Max Act: 5.7773. Min Act: -0.1700
Data Index: 4362111 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19