Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1652 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8967. Min Range: -3.8967
Max Act: 3.8967. Min Act: -0.1700
Data Index: 1476926 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8967. Min Range: -3.8967
Max Act: 3.8654. Min Act: -0.1700
Data Index: 3272400 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8967. Min Range: -3.8967
Max Act: 3.8654. Min Act: -0.1700
Data Index: 8776689 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8967. Min Range: -3.8967
Max Act: 3.8654. Min Act: -0.1700
Data Index: 6081386 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8967. Min Range: -3.8967
Max Act: 3.8654. Min Act: -0.1700
Data Index: 1835418 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8967. Min Range: -3.8967
Max Act: 3.8654. Min Act: -0.1700
Data Index: 4033251 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8967. Min Range: -3.8967
Max Act: 3.8342. Min Act: -0.1700
Data Index: 6520395 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8967. Min Range: -3.8967
Max Act: 3.7716. Min Act: -0.1700
Data Index: 8047363 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8967. Min Range: -3.8967
Max Act: 3.8029. Min Act: -0.1700
Data Index: 3124720 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8967. Min Range: -3.8967
Max Act: 3.8029. Min Act: -0.1700
Data Index: 7724481 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8967. Min Range: -3.8967
Max Act: 3.7716. Min Act: -0.1700
Data Index: 4087766 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8967. Min Range: -3.8967
Max Act: 3.7403. Min Act: -0.1700
Data Index: 7340697 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8967. Min Range: -3.8967
Max Act: 3.7716. Min Act: -0.1700
Data Index: 3429635 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8967. Min Range: -3.8967
Max Act: 3.7716. Min Act: -0.1700
Data Index: 7027826 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8967. Min Range: -3.8967
Max Act: 3.8029. Min Act: -0.1700
Data Index: 744432 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8967. Min Range: -3.8967
Max Act: 3.7716. Min Act: -0.1700
Data Index: 1647382 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8967. Min Range: -3.8967
Max Act: 3.7716. Min Act: -0.1700
Data Index: 1594350 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8967. Min Range: -3.8967
Max Act: 3.7716. Min Act: -0.1700
Data Index: 555403 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8967. Min Range: -3.8967
Max Act: 3.7716. Min Act: -0.1700
Data Index: 6512694 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8967. Min Range: -3.8967
Max Act: 3.7403. Min Act: -0.1700
Data Index: 3133276 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19