Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2905 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8135. Min Range: -5.8135
Max Act: 5.8135. Min Act: -0.1700
Data Index: 2311883 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8135. Min Range: -5.8135
Max Act: 5.5947. Min Act: -0.1700
Data Index: 4753797 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8135. Min Range: -5.8135
Max Act: 5.5947. Min Act: -0.1700
Data Index: 8153011 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8135. Min Range: -5.8135
Max Act: 5.5635. Min Act: -0.1700
Data Index: 6779124 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8135. Min Range: -5.8135
Max Act: 5.5322. Min Act: -0.1700
Data Index: 4743100 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8135. Min Range: -5.8135
Max Act: 5.5322. Min Act: -0.1700
Data Index: 7209764 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8135. Min Range: -5.8135
Max Act: 5.5322. Min Act: -0.1700
Data Index: 6029323 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8135. Min Range: -5.8135
Max Act: 5.4697. Min Act: -0.1700
Data Index: 8091482 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8135. Min Range: -5.8135
Max Act: 5.5010. Min Act: -0.1700
Data Index: 754980 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8135. Min Range: -5.8135
Max Act: 5.4385. Min Act: -0.1700
Data Index: 2190263 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8135. Min Range: -5.8135
Max Act: 5.4385. Min Act: -0.1700
Data Index: 5914506 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8135. Min Range: -5.8135
Max Act: 5.4385. Min Act: -0.1700
Data Index: 5505629 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8135. Min Range: -5.8135
Max Act: 5.4072. Min Act: -0.1700
Data Index: 7763661 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8135. Min Range: -5.8135
Max Act: 5.4072. Min Act: -0.1700
Data Index: 6939891 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8135. Min Range: -5.8135
Max Act: 5.3760. Min Act: -0.1700
Data Index: 6441204 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8135. Min Range: -5.8135
Max Act: 5.3447. Min Act: -0.1700
Data Index: 3066307 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8135. Min Range: -5.8135
Max Act: 5.3447. Min Act: -0.1700
Data Index: 3332690 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8135. Min Range: -5.8135
Max Act: 5.3760. Min Act: -0.1700
Data Index: 7565326 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8135. Min Range: -5.8135
Max Act: 5.3135. Min Act: -0.1700
Data Index: 1672219 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8135. Min Range: -5.8135
Max Act: 5.3135. Min Act: -0.1700
Data Index: 7187117 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19