Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3716 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8838. Min Range: -2.8838
Max Act: 2.8838. Min Act: -0.1700
Data Index: 1204746 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8838. Min Range: -2.8838
Max Act: 2.8679. Min Act: -0.1700
Data Index: 7730494 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8838. Min Range: -2.8838
Max Act: 2.8520. Min Act: -0.1700
Data Index: 3472159 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8838. Min Range: -2.8838
Max Act: 2.8520. Min Act: -0.1700
Data Index: 1794942 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8838. Min Range: -2.8838
Max Act: 2.8361. Min Act: -0.1700
Data Index: 2703831 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8838. Min Range: -2.8838
Max Act: 2.8361. Min Act: -0.1700
Data Index: 2650745 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8838. Min Range: -2.8838
Max Act: 2.8361. Min Act: -0.1700
Data Index: 7907377 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8838. Min Range: -2.8838
Max Act: 2.8361. Min Act: -0.1700
Data Index: 1762293 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8838. Min Range: -2.8838
Max Act: 2.8361. Min Act: -0.1700
Data Index: 5765842 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8838. Min Range: -2.8838
Max Act: 2.8202. Min Act: -0.1700
Data Index: 1442875 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8838. Min Range: -2.8838
Max Act: 2.8202. Min Act: -0.1700
Data Index: 428634 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8838. Min Range: -2.8838
Max Act: 2.8202. Min Act: -0.1700
Data Index: 1593128 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8838. Min Range: -2.8838
Max Act: 2.8202. Min Act: -0.1700
Data Index: 4067393 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8838. Min Range: -2.8838
Max Act: 2.8202. Min Act: -0.1700
Data Index: 2055141 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8838. Min Range: -2.8838
Max Act: 2.8043. Min Act: -0.1700
Data Index: 4561204 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8838. Min Range: -2.8838
Max Act: 2.8043. Min Act: -0.1700
Data Index: 5860057 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8838. Min Range: -2.8838
Max Act: 2.8043. Min Act: -0.1700
Data Index: 1678081 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8838. Min Range: -2.8838
Max Act: 2.8043. Min Act: -0.1700
Data Index: 5339823 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8838. Min Range: -2.8838
Max Act: 2.7884. Min Act: -0.1700
Data Index: 2972012 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8838. Min Range: -2.8838
Max Act: 2.7884. Min Act: -0.1700
Data Index: 796578 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19