Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2003 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1354. Min Range: -5.1354
Max Act: 5.1354. Min Act: -0.1700
Data Index: 1363971 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1354. Min Range: -5.1354
Max Act: 5.1041. Min Act: -0.1700
Data Index: 7219471 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1354. Min Range: -5.1354
Max Act: 5.1041. Min Act: -0.1700
Data Index: 4744492 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1354. Min Range: -5.1354
Max Act: 5.1041. Min Act: -0.1700
Data Index: 4046545 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1354. Min Range: -5.1354
Max Act: 5.0729. Min Act: -0.1700
Data Index: 6731965 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1354. Min Range: -5.1354
Max Act: 5.0729. Min Act: -0.1700
Data Index: 4597731 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1354. Min Range: -5.1354
Max Act: 5.0416. Min Act: -0.1700
Data Index: 3550236 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1354. Min Range: -5.1354
Max Act: 5.0416. Min Act: -0.1700
Data Index: 3459024 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1354. Min Range: -5.1354
Max Act: 5.0416. Min Act: -0.1700
Data Index: 3676668 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1354. Min Range: -5.1354
Max Act: 5.0104. Min Act: -0.1700
Data Index: 1443072 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1354. Min Range: -5.1354
Max Act: 5.0416. Min Act: -0.1700
Data Index: 2771585 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1354. Min Range: -5.1354
Max Act: 4.9791. Min Act: -0.1700
Data Index: 8260895 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1354. Min Range: -5.1354
Max Act: 4.9791. Min Act: -0.1700
Data Index: 3467302 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1354. Min Range: -5.1354
Max Act: 5.0104. Min Act: -0.1700
Data Index: 522585 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1354. Min Range: -5.1354
Max Act: 5.0104. Min Act: -0.1700
Data Index: 1031948 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1354. Min Range: -5.1354
Max Act: 5.0104. Min Act: -0.1700
Data Index: 7654067 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1354. Min Range: -5.1354
Max Act: 4.9791. Min Act: -0.1700
Data Index: 2126642 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1354. Min Range: -5.1354
Max Act: 5.0104. Min Act: -0.1700
Data Index: 8304874 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1354. Min Range: -5.1354
Max Act: 4.9791. Min Act: -0.1700
Data Index: 1837140 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1354. Min Range: -5.1354
Max Act: 4.9166. Min Act: -0.1700
Data Index: 4556175 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19