Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3203 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0515. Min Range: -4.0515
Max Act: 4.0515. Min Act: -0.1700
Data Index: 8727285 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0515. Min Range: -4.0515
Max Act: 4.0203. Min Act: -0.1700
Data Index: 4477749 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0515. Min Range: -4.0515
Max Act: 3.9890. Min Act: -0.1700
Data Index: 5987965 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0515. Min Range: -4.0515
Max Act: 3.9890. Min Act: -0.1700
Data Index: 8595709 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0515. Min Range: -4.0515
Max Act: 3.9890. Min Act: -0.1697
Data Index: 8315617 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0515. Min Range: -4.0515
Max Act: 3.8952. Min Act: -0.1700
Data Index: 3317077 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0515. Min Range: -4.0515
Max Act: 3.8639. Min Act: -0.1700
Data Index: 8328112 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0515. Min Range: -4.0515
Max Act: 3.8639. Min Act: -0.1700
Data Index: 2111016 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0515. Min Range: -4.0515
Max Act: 3.8639. Min Act: -0.1700
Data Index: 8315618 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0515. Min Range: -4.0515
Max Act: 3.8327. Min Act: -0.1700
Data Index: 3578273 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0515. Min Range: -4.0515
Max Act: 3.8327. Min Act: -0.1700
Data Index: 4954567 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0515. Min Range: -4.0515
Max Act: 3.8327. Min Act: -0.1700
Data Index: 2111019 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0515. Min Range: -4.0515
Max Act: 3.8014. Min Act: -0.1700
Data Index: 7697447 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0515. Min Range: -4.0515
Max Act: 3.8014. Min Act: -0.1700
Data Index: 4029682 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0515. Min Range: -4.0515
Max Act: 3.7701. Min Act: -0.1700
Data Index: 5527418 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0515. Min Range: -4.0515
Max Act: 3.7701. Min Act: -0.1700
Data Index: 1658028 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0515. Min Range: -4.0515
Max Act: 3.7701. Min Act: -0.1700
Data Index: 6152541 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0515. Min Range: -4.0515
Max Act: 3.7389. Min Act: -0.1700
Data Index: 569976 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0515. Min Range: -4.0515
Max Act: 3.7076. Min Act: -0.1700
Data Index: 699672 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0515. Min Range: -4.0515
Max Act: 3.7076. Min Act: -0.1700
Data Index: 4029686 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19