Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 198 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0732. Min Range: -5.0732
Max Act: 5.0732. Min Act: -0.1700
Data Index: 3699967 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.9794. Min Act: -0.1700
Data Index: 3598646 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.8857. Min Act: -0.1700
Data Index: 4175979 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.8857. Min Act: -0.1700
Data Index: 4237736 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.9169. Min Act: -0.1700
Data Index: 3663176 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.8857. Min Act: -0.1700
Data Index: 5967739 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.8544. Min Act: -0.1700
Data Index: 4236902 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.8232. Min Act: -0.1700
Data Index: 4180403 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.8232. Min Act: -0.1700
Data Index: 997572 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.8232. Min Act: -0.1700
Data Index: 2350990 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.7607. Min Act: -0.1700
Data Index: 848173 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.7607. Min Act: -0.1700
Data Index: 5687133 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.7607. Min Act: -0.1700
Data Index: 6313019 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.7294. Min Act: -0.1700
Data Index: 1543660 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.7294. Min Act: -0.1700
Data Index: 4496577 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.7294. Min Act: -0.1700
Data Index: 300841 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.7294. Min Act: -0.1700
Data Index: 2713782 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.7294. Min Act: -0.1700
Data Index: 8316365 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.6982. Min Act: -0.1700
Data Index: 4865495 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0732. Min Range: -5.0732
Max Act: 4.7294. Min Act: -0.1700
Data Index: 4286695 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #19