Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2808 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2590. Min Range: -2.2590
Max Act: 2.2590. Min Act: -0.1700
Data Index: 48775 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2590. Min Range: -2.2590
Max Act: 2.2425. Min Act: -0.1700
Data Index: 2195988 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2590. Min Range: -2.2590
Max Act: 2.2094. Min Act: -0.1700
Data Index: 3298965 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2590. Min Range: -2.2590
Max Act: 2.2260. Min Act: -0.1700
Data Index: 6384981 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2590. Min Range: -2.2590
Max Act: 2.2260. Min Act: -0.1700
Data Index: 6844346 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2590. Min Range: -2.2590
Max Act: 2.1928. Min Act: -0.1700
Data Index: 5836456 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2590. Min Range: -2.2590
Max Act: 2.1928. Min Act: -0.1700
Data Index: 2619331 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2590. Min Range: -2.2590
Max Act: 2.2094. Min Act: -0.1700
Data Index: 6126377 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2590. Min Range: -2.2590
Max Act: 2.1762. Min Act: -0.1700
Data Index: 8071312 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2590. Min Range: -2.2590
Max Act: 2.1596. Min Act: -0.1700
Data Index: 1978731 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2590. Min Range: -2.2590
Max Act: 2.1762. Min Act: -0.1700
Data Index: 807538 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2590. Min Range: -2.2590
Max Act: 2.2094. Min Act: -0.1700
Data Index: 3931859 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2590. Min Range: -2.2590
Max Act: 2.1596. Min Act: -0.1700
Data Index: 6717844 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2590. Min Range: -2.2590
Max Act: 2.1596. Min Act: -0.1700
Data Index: 260296 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2590. Min Range: -2.2590
Max Act: 2.1762. Min Act: -0.1700
Data Index: 8238689 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2590. Min Range: -2.2590
Max Act: 2.1762. Min Act: -0.1700
Data Index: 6651779 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2590. Min Range: -2.2590
Max Act: 2.1928. Min Act: -0.1700
Data Index: 4727645 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2590. Min Range: -2.2590
Max Act: 2.1762. Min Act: -0.1700
Data Index: 3907898 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2590. Min Range: -2.2590
Max Act: 2.1762. Min Act: -0.1700
Data Index: 6888828 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2590. Min Range: -2.2590
Max Act: 2.1596. Min Act: -0.1700
Data Index: 1411914 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19