Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6116 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3334. Min Range: -4.3334
Max Act: 4.3334. Min Act: -0.1700
Data Index: 345684 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3334. Min Range: -4.3334
Max Act: 4.1771. Min Act: -0.1700
Data Index: 8177305 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3334. Min Range: -4.3334
Max Act: 4.1146. Min Act: -0.1700
Data Index: 2687662 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3334. Min Range: -4.3334
Max Act: 4.1146. Min Act: -0.1700
Data Index: 5941119 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3334. Min Range: -4.3334
Max Act: 4.1146. Min Act: -0.1700
Data Index: 355896 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3334. Min Range: -4.3334
Max Act: 4.0521. Min Act: -0.1700
Data Index: 355094 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3334. Min Range: -4.3334
Max Act: 4.0208. Min Act: -0.1700
Data Index: 6479493 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3334. Min Range: -4.3334
Max Act: 3.9896. Min Act: -0.1700
Data Index: 1300896 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3334. Min Range: -4.3334
Max Act: 3.9583. Min Act: -0.1700
Data Index: 581176 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3334. Min Range: -4.3334
Max Act: 3.9583. Min Act: -0.1700
Data Index: 4156184 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3334. Min Range: -4.3334
Max Act: 3.9271. Min Act: -0.1700
Data Index: 7507269 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3334. Min Range: -4.3334
Max Act: 3.8958. Min Act: -0.1700
Data Index: 6135566 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3334. Min Range: -4.3334
Max Act: 3.8958. Min Act: -0.1700
Data Index: 7834625 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3334. Min Range: -4.3334
Max Act: 3.8958. Min Act: -0.1700
Data Index: 8259493 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3334. Min Range: -4.3334
Max Act: 3.8958. Min Act: -0.1700
Data Index: 7798695 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3334. Min Range: -4.3334
Max Act: 3.9271. Min Act: -0.1700
Data Index: 6459529 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3334. Min Range: -4.3334
Max Act: 3.9271. Min Act: -0.1700
Data Index: 7044091 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3334. Min Range: -4.3334
Max Act: 3.8958. Min Act: -0.1700
Data Index: 5741370 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3334. Min Range: -4.3334
Max Act: 3.8958. Min Act: -0.1700
Data Index: 245488 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3334. Min Range: -4.3334
Max Act: 3.8645. Min Act: -0.1700
Data Index: 917934 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #19