Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2854 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0536. Min Range: -6.0536
Max Act: 6.0536. Min Act: -0.1700
Data Index: 7171216 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0536. Min Range: -6.0536
Max Act: 6.0224. Min Act: -0.1700
Data Index: 7889881 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.8349. Min Act: -0.1700
Data Index: 890314 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.7724. Min Act: -0.1700
Data Index: 4314506 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.7724. Min Act: -0.1700
Data Index: 3431283 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.7411. Min Act: -0.1700
Data Index: 864323 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.7411. Min Act: -0.1700
Data Index: 7878037 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.7099. Min Act: -0.1700
Data Index: 60680 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.6786. Min Act: -0.1700
Data Index: 7949138 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.6786. Min Act: -0.1700
Data Index: 2150502 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.6474. Min Act: -0.1700
Data Index: 2396407 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.6161. Min Act: -0.1700
Data Index: 4515241 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.6161. Min Act: -0.1700
Data Index: 2156891 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.6161. Min Act: -0.1700
Data Index: 5390311 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.5849. Min Act: -0.1700
Data Index: 1573258 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.5849. Min Act: -0.1700
Data Index: 6954056 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.5849. Min Act: -0.1700
Data Index: 8685852 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.5849. Min Act: -0.1700
Data Index: 3785166 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.5849. Min Act: -0.1700
Data Index: 1990268 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0536. Min Range: -6.0536
Max Act: 5.5536. Min Act: -0.1700
Data Index: 3420750 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19