Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3904 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2472. Min Range: -5.2472
Max Act: 5.2472. Min Act: -0.1700
Data Index: 6562153 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2472. Min Range: -5.2472
Max Act: 5.0909. Min Act: -0.1700
Data Index: 2344836 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2472. Min Range: -5.2472
Max Act: 4.9659. Min Act: -0.1700
Data Index: 6098986 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2472. Min Range: -5.2472
Max Act: 4.9347. Min Act: -0.1700
Data Index: 4165113 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2472. Min Range: -5.2472
Max Act: 4.8722. Min Act: -0.1700
Data Index: 1357536 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2472. Min Range: -5.2472
Max Act: 4.7472. Min Act: -0.1700
Data Index: 2080107 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2472. Min Range: -5.2472
Max Act: 4.7784. Min Act: -0.1700
Data Index: 5641236 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2472. Min Range: -5.2472
Max Act: 4.7472. Min Act: -0.1700
Data Index: 7112416 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2472. Min Range: -5.2472
Max Act: 4.7472. Min Act: -0.1700
Data Index: 250627 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2472. Min Range: -5.2472
Max Act: 4.7472. Min Act: -0.1700
Data Index: 5573599 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2472. Min Range: -5.2472
Max Act: 4.7159. Min Act: -0.1700
Data Index: 8412344 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2472. Min Range: -5.2472
Max Act: 4.7159. Min Act: -0.1700
Data Index: 3027781 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2472. Min Range: -5.2472
Max Act: 4.6846. Min Act: -0.1700
Data Index: 2099060 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2472. Min Range: -5.2472
Max Act: 4.7159. Min Act: -0.1700
Data Index: 6831115 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2472. Min Range: -5.2472
Max Act: 4.6846. Min Act: -0.1700
Data Index: 81044 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2472. Min Range: -5.2472
Max Act: 4.6534. Min Act: -0.1700
Data Index: 1353149 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2472. Min Range: -5.2472
Max Act: 4.6534. Min Act: -0.1700
Data Index: 4222716 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2472. Min Range: -5.2472
Max Act: 4.6534. Min Act: -0.1700
Data Index: 6203773 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2472. Min Range: -5.2472
Max Act: 4.6846. Min Act: -0.1700
Data Index: 4779140 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2472. Min Range: -5.2472
Max Act: 4.6221. Min Act: -0.1700
Data Index: 1681695 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19