Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 998 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0201. Min Range: -4.0201
Max Act: 4.0201. Min Act: -0.1700
Data Index: 7198799 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0201. Min Range: -4.0201
Max Act: 4.0201. Min Act: -0.1700
Data Index: 4454779 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0201. Min Range: -4.0201
Max Act: 4.0201. Min Act: -0.1700
Data Index: 6941182 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.9575. Min Act: -0.1700
Data Index: 3346658 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.9575. Min Act: -0.1700
Data Index: 5390869 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.9575. Min Act: -0.1700
Data Index: 3667090 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.9263. Min Act: -0.1700
Data Index: 6063326 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.9263. Min Act: -0.1700
Data Index: 5343862 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8950. Min Act: -0.1700
Data Index: 4580739 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8950. Min Act: -0.1700
Data Index: 4445159 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8794. Min Act: -0.1700
Data Index: 3272252 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8794. Min Act: -0.1700
Data Index: 1246656 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8637. Min Act: -0.1700
Data Index: 8133366 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8637. Min Act: -0.1700
Data Index: 7990632 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8168. Min Act: -0.1700
Data Index: 5838575 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8325. Min Act: -0.1700
Data Index: 3531757 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8481. Min Act: -0.1700
Data Index: 5354011 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8325. Min Act: -0.1700
Data Index: 1941221 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8481. Min Act: -0.1700
Data Index: 8417523 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8637. Min Act: -0.1700
Data Index: 2762275 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #19