Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5770 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0902. Min Range: -6.0902
Max Act: 6.0902. Min Act: -0.1700
Data Index: 7897748 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0902. Min Range: -6.0902
Max Act: 6.0589. Min Act: -0.1700
Data Index: 3846999 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0902. Min Range: -6.0902
Max Act: 5.9964. Min Act: -0.1700
Data Index: 7082187 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0902. Min Range: -6.0902
Max Act: 5.8714. Min Act: -0.1700
Data Index: 6177303 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0902. Min Range: -6.0902
Max Act: 5.9027. Min Act: -0.1700
Data Index: 5998730 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0902. Min Range: -6.0902
Max Act: 5.8402. Min Act: -0.1700
Data Index: 1463958 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0902. Min Range: -6.0902
Max Act: 5.8402. Min Act: -0.1700
Data Index: 5368199 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0902. Min Range: -6.0902
Max Act: 5.8402. Min Act: -0.1700
Data Index: 1201358 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0902. Min Range: -6.0902
Max Act: 5.8089. Min Act: -0.1700
Data Index: 5657684 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0902. Min Range: -6.0902
Max Act: 5.8089. Min Act: -0.1700
Data Index: 3164445 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0902. Min Range: -6.0902
Max Act: 5.7464. Min Act: -0.1700
Data Index: 4600050 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0902. Min Range: -6.0902
Max Act: 5.7777. Min Act: -0.1700
Data Index: 2309750 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0902. Min Range: -6.0902
Max Act: 5.7464. Min Act: -0.1700
Data Index: 3589355 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0902. Min Range: -6.0902
Max Act: 5.7464. Min Act: -0.1700
Data Index: 4612443 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0902. Min Range: -6.0902
Max Act: 5.7464. Min Act: -0.1700
Data Index: 5611362 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0902. Min Range: -6.0902
Max Act: 5.7152. Min Act: -0.1700
Data Index: 2600630 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0902. Min Range: -6.0902
Max Act: 5.7152. Min Act: -0.1700
Data Index: 5348680 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0902. Min Range: -6.0902
Max Act: 5.6839. Min Act: -0.1700
Data Index: 6793786 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0902. Min Range: -6.0902
Max Act: 5.7152. Min Act: -0.1700
Data Index: 5177233 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0902. Min Range: -6.0902
Max Act: 5.7152. Min Act: -0.1700
Data Index: 85664 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19