Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3604 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7009. Min Range: -5.7009
Max Act: 5.7009. Min Act: -0.1699
Data Index: 4239603 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7009. Min Range: -5.7009
Max Act: 5.6384. Min Act: -0.1700
Data Index: 6339479 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7009. Min Range: -5.7009
Max Act: 5.6697. Min Act: -0.1700
Data Index: 7545301 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7009. Min Range: -5.7009
Max Act: 5.5759. Min Act: -0.1700
Data Index: 7424930 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7009. Min Range: -5.7009
Max Act: 5.5759. Min Act: -0.1700
Data Index: 4451472 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7009. Min Range: -5.7009
Max Act: 5.5447. Min Act: -0.1700
Data Index: 2906652 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7009. Min Range: -5.7009
Max Act: 5.4822. Min Act: -0.1700
Data Index: 5019640 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7009. Min Range: -5.7009
Max Act: 5.4509. Min Act: -0.1700
Data Index: 8425899 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7009. Min Range: -5.7009
Max Act: 5.4509. Min Act: -0.1698
Data Index: 7842640 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7009. Min Range: -5.7009
Max Act: 5.4509. Min Act: -0.1700
Data Index: 4594632 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7009. Min Range: -5.7009
Max Act: 5.4509. Min Act: -0.1700
Data Index: 2650063 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7009. Min Range: -5.7009
Max Act: 5.4822. Min Act: -0.1700
Data Index: 7310734 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7009. Min Range: -5.7009
Max Act: 5.4822. Min Act: -0.1700
Data Index: 4683101 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7009. Min Range: -5.7009
Max Act: 5.4509. Min Act: -0.1700
Data Index: 3245915 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7009. Min Range: -5.7009
Max Act: 5.4197. Min Act: -0.1700
Data Index: 4529207 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7009. Min Range: -5.7009
Max Act: 5.4197. Min Act: -0.1700
Data Index: 4523648 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7009. Min Range: -5.7009
Max Act: 5.4197. Min Act: -0.1700
Data Index: 7599817 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7009. Min Range: -5.7009
Max Act: 5.4197. Min Act: -0.1700
Data Index: 4818254 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7009. Min Range: -5.7009
Max Act: 5.4197. Min Act: -0.1700
Data Index: 2130065 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7009. Min Range: -5.7009
Max Act: 5.4197. Min Act: -0.1700
Data Index: 6789645 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19