Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 944 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8948. Min Range: -3.8948
Max Act: 3.8948. Min Act: -0.1700
Data Index: 3701317 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8948. Min Range: -3.8948
Max Act: 3.8322. Min Act: -0.1700
Data Index: 1633326 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8948. Min Range: -3.8948
Max Act: 3.8322. Min Act: -0.1700
Data Index: 7937374 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8948. Min Range: -3.8948
Max Act: 3.8322. Min Act: -0.1700
Data Index: 4629422 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8948. Min Range: -3.8948
Max Act: 3.8010. Min Act: -0.1700
Data Index: 5823260 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8948. Min Range: -3.8948
Max Act: 3.8010. Min Act: -0.1700
Data Index: 6073631 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8948. Min Range: -3.8948
Max Act: 3.8010. Min Act: -0.1700
Data Index: 904125 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8948. Min Range: -3.8948
Max Act: 3.8010. Min Act: -0.1700
Data Index: 901270 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8948. Min Range: -3.8948
Max Act: 3.7697. Min Act: -0.1700
Data Index: 5812771 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8948. Min Range: -3.8948
Max Act: 3.7697. Min Act: -0.1700
Data Index: 2848495 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8948. Min Range: -3.8948
Max Act: 3.7697. Min Act: -0.1700
Data Index: 4246165 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8948. Min Range: -3.8948
Max Act: 3.7697. Min Act: -0.1700
Data Index: 3161544 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8948. Min Range: -3.8948
Max Act: 3.7541. Min Act: -0.1700
Data Index: 8249791 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8948. Min Range: -3.8948
Max Act: 3.7541. Min Act: -0.1700
Data Index: 948299 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8948. Min Range: -3.8948
Max Act: 3.7541. Min Act: -0.1700
Data Index: 2415020 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8948. Min Range: -3.8948
Max Act: 3.7541. Min Act: -0.1700
Data Index: 8392841 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8948. Min Range: -3.8948
Max Act: 3.7541. Min Act: -0.1700
Data Index: 8461704 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8948. Min Range: -3.8948
Max Act: 3.7541. Min Act: -0.1700
Data Index: 7260396 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8948. Min Range: -3.8948
Max Act: 3.7541. Min Act: -0.1700
Data Index: 2775200 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8948. Min Range: -3.8948
Max Act: 3.7541. Min Act: -0.1700
Data Index: 1007638 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19