Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2691 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.8361. Min Act: -0.1700
Data Index: 1327718 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.8048. Min Act: -0.1700
Data Index: 560320 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.7736. Min Act: -0.1700
Data Index: 7782315 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.7423. Min Act: -0.1700
Data Index: 7774330 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.7111. Min Act: -0.1700
Data Index: 8512890 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.7111. Min Act: -0.1700
Data Index: 8399593 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.7111. Min Act: -0.1700
Data Index: 4187030 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.7111. Min Act: -0.1700
Data Index: 1706071 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.7423. Min Act: -0.1700
Data Index: 7856153 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.6798. Min Act: -0.1700
Data Index: 7043628 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.6486. Min Act: -0.1700
Data Index: 4394240 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.7111. Min Act: -0.1700
Data Index: 1769989 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.6798. Min Act: -0.1700
Data Index: 911029 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.6798. Min Act: -0.1700
Data Index: 8054865 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.6798. Min Act: -0.1700
Data Index: 4689665 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.6486. Min Act: -0.1700
Data Index: 4259643 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.5861. Min Act: -0.1700
Data Index: 2624690 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.6173. Min Act: -0.1700
Data Index: 1979169 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.6173. Min Act: -0.1700
Data Index: 8086341 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8361. Min Range: -4.8361
Max Act: 4.5861. Min Act: -0.1700
Data Index: 5070413 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #19