Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3088 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.8135. Min Act: -0.1700
Data Index: 5081054 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.5948. Min Act: -0.1700
Data Index: 2132482 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.5635. Min Act: -0.1700
Data Index: 4588516 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.5635. Min Act: -0.1700
Data Index: 5129055 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.5323. Min Act: -0.1700
Data Index: 1434988 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.5323. Min Act: -0.1700
Data Index: 1725464 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.5010. Min Act: -0.1700
Data Index: 179431 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.4698. Min Act: -0.1700
Data Index: 2796652 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.5010. Min Act: -0.1700
Data Index: 4666386 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.4698. Min Act: -0.1700
Data Index: 3489197 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.4698. Min Act: -0.1700
Data Index: 835507 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.4385. Min Act: -0.1700
Data Index: 8586079 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.4385. Min Act: -0.1700
Data Index: 2376260 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.3760. Min Act: -0.1700
Data Index: 7189357 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.3760. Min Act: -0.1700
Data Index: 5974227 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.3760. Min Act: -0.1700
Data Index: 3971465 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.3760. Min Act: -0.1700
Data Index: 7466488 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.3760. Min Act: -0.1700
Data Index: 1858726 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.3448. Min Act: -0.1700
Data Index: 1429913 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8135. Min Range: -6.8135
Max Act: 6.3760. Min Act: -0.1700
Data Index: 4623931 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #19