Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3247 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7204. Min Range: -2.7204
Max Act: 2.7204. Min Act: -0.1700
Data Index: 5209491 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7204. Min Range: -2.7204
Max Act: 2.6884. Min Act: -0.1700
Data Index: 1283521 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7204. Min Range: -2.7204
Max Act: 2.6724. Min Act: -0.1700
Data Index: 5779176 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7204. Min Range: -2.7204
Max Act: 2.6724. Min Act: -0.1700
Data Index: 4707631 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7204. Min Range: -2.7204
Max Act: 2.6403. Min Act: -0.1700
Data Index: 3380801 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7204. Min Range: -2.7204
Max Act: 2.6564. Min Act: -0.1700
Data Index: 1578210 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7204. Min Range: -2.7204
Max Act: 2.6243. Min Act: -0.1700
Data Index: 6188066 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7204. Min Range: -2.7204
Max Act: 2.6403. Min Act: -0.1700
Data Index: 6272775 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7204. Min Range: -2.7204
Max Act: 2.6243. Min Act: -0.1700
Data Index: 7305774 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7204. Min Range: -2.7204
Max Act: 2.6403. Min Act: -0.1700
Data Index: 4827037 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7204. Min Range: -2.7204
Max Act: 2.6243. Min Act: -0.1700
Data Index: 4967991 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7204. Min Range: -2.7204
Max Act: 2.6082. Min Act: -0.1700
Data Index: 2035123 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7204. Min Range: -2.7204
Max Act: 2.6082. Min Act: -0.1700
Data Index: 5010513 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7204. Min Range: -2.7204
Max Act: 2.6082. Min Act: -0.1700
Data Index: 4140584 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7204. Min Range: -2.7204
Max Act: 2.5921. Min Act: -0.1700
Data Index: 5353228 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7204. Min Range: -2.7204
Max Act: 2.6082. Min Act: -0.1700
Data Index: 8299253 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7204. Min Range: -2.7204
Max Act: 2.5598. Min Act: -0.1700
Data Index: 1958842 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7204. Min Range: -2.7204
Max Act: 2.5921. Min Act: -0.1700
Data Index: 5124385 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7204. Min Range: -2.7204
Max Act: 2.6403. Min Act: -0.1700
Data Index: 1267636 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7204. Min Range: -2.7204
Max Act: 2.5921. Min Act: -0.1700
Data Index: 6798240 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19