Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1095 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7787. Min Range: -3.7787
Max Act: 3.7787. Min Act: -0.1700
Data Index: 2233121 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7787. Min Range: -3.7787
Max Act: 3.7787. Min Act: -0.1700
Data Index: 4235570 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7787. Min Range: -3.7787
Max Act: 3.7787. Min Act: -0.1700
Data Index: 4772958 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7787. Min Range: -3.7787
Max Act: 3.7631. Min Act: -0.1700
Data Index: 8647126 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7787. Min Range: -3.7787
Max Act: 3.7474. Min Act: -0.1700
Data Index: 5929352 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7787. Min Range: -3.7787
Max Act: 3.7318. Min Act: -0.1700
Data Index: 5491503 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7787. Min Range: -3.7787
Max Act: 3.7318. Min Act: -0.1700
Data Index: 6540764 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7787. Min Range: -3.7787
Max Act: 3.7318. Min Act: -0.1700
Data Index: 1319504 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7787. Min Range: -3.7787
Max Act: 3.7162. Min Act: -0.1700
Data Index: 2497164 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7787. Min Range: -3.7787
Max Act: 3.7162. Min Act: -0.1700
Data Index: 2736437 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7787. Min Range: -3.7787
Max Act: 3.7005. Min Act: -0.1700
Data Index: 6338800 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7787. Min Range: -3.7787
Max Act: 3.6849. Min Act: -0.1700
Data Index: 425424 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7787. Min Range: -3.7787
Max Act: 3.7005. Min Act: -0.1700
Data Index: 8716453 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7787. Min Range: -3.7787
Max Act: 3.6692. Min Act: -0.1700
Data Index: 1488518 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7787. Min Range: -3.7787
Max Act: 3.6536. Min Act: -0.1700
Data Index: 4544600 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7787. Min Range: -3.7787
Max Act: 3.6849. Min Act: -0.1700
Data Index: 2081451 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7787. Min Range: -3.7787
Max Act: 3.6692. Min Act: -0.1700
Data Index: 761085 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7787. Min Range: -3.7787
Max Act: 3.6379. Min Act: -0.1700
Data Index: 8499842 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7787. Min Range: -3.7787
Max Act: 3.6536. Min Act: -0.1700
Data Index: 3205784 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7787. Min Range: -3.7787
Max Act: 3.6379. Min Act: -0.1700
Data Index: 5985655 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19