Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 664 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1694. Min Range: -2.1694
Max Act: 2.1694. Min Act: -0.1700
Data Index: 5355127 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1694. Min Range: -2.1694
Max Act: 2.1361. Min Act: -0.1700
Data Index: 5145098 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1694. Min Range: -2.1694
Max Act: 2.1361. Min Act: -0.1700
Data Index: 4943036 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1694. Min Range: -2.1694
Max Act: 2.1027. Min Act: -0.1700
Data Index: 4777868 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1694. Min Range: -2.1694
Max Act: 2.1194. Min Act: -0.1700
Data Index: 8361512 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1694. Min Range: -2.1694
Max Act: 2.1361. Min Act: -0.1700
Data Index: 1965763 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1694. Min Range: -2.1694
Max Act: 2.0859. Min Act: -0.1700
Data Index: 310485 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1694. Min Range: -2.1694
Max Act: 2.0859. Min Act: -0.1700
Data Index: 1715102 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1694. Min Range: -2.1694
Max Act: 2.0859. Min Act: -0.1700
Data Index: 4019183 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1694. Min Range: -2.1694
Max Act: 2.0859. Min Act: -0.1700
Data Index: 4664617 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1694. Min Range: -2.1694
Max Act: 2.0691. Min Act: -0.1700
Data Index: 8523206 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1694. Min Range: -2.1694
Max Act: 2.0691. Min Act: -0.1700
Data Index: 2410849 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1694. Min Range: -2.1694
Max Act: 2.0691. Min Act: -0.1700
Data Index: 736330 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1694. Min Range: -2.1694
Max Act: 2.0691. Min Act: -0.1700
Data Index: 3657377 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1694. Min Range: -2.1694
Max Act: 2.0691. Min Act: -0.1700
Data Index: 5868322 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1694. Min Range: -2.1694
Max Act: 2.0859. Min Act: -0.1700
Data Index: 6045546 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1694. Min Range: -2.1694
Max Act: 2.0691. Min Act: -0.1700
Data Index: 5093984 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1694. Min Range: -2.1694
Max Act: 2.0691. Min Act: -0.1700
Data Index: 736341 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1694. Min Range: -2.1694
Max Act: 2.0523. Min Act: -0.1700
Data Index: 5104017 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1694. Min Range: -2.1694
Max Act: 2.0691. Min Act: -0.1700
Data Index: 5108791 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19