Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3685 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.6981. Min Act: -0.1700
Data Index: 2168501 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.6981. Min Act: -0.1700
Data Index: 8043115 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.6981. Min Act: -0.1700
Data Index: 4640195 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.6981. Min Act: -0.1700
Data Index: 1161156 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.6981. Min Act: -0.1700
Data Index: 8830284 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.6981. Min Act: -0.1700
Data Index: 8269392 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.6669. Min Act: -0.1700
Data Index: 3664539 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.6669. Min Act: -0.1700
Data Index: 742142 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.6669. Min Act: -0.1700
Data Index: 3532361 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.6669. Min Act: -0.1700
Data Index: 4682536 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.6669. Min Act: -0.1700
Data Index: 4741337 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.6669. Min Act: -0.1700
Data Index: 7319256 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.6669. Min Act: -0.1700
Data Index: 7360365 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.6669. Min Act: -0.1700
Data Index: 1765395 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.6356. Min Act: -0.1700
Data Index: 3670028 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.6356. Min Act: -0.1700
Data Index: 3798927 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.6356. Min Act: -0.1699
Data Index: 4331574 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.6356. Min Act: -0.1700
Data Index: 482194 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.6356. Min Act: -0.1699
Data Index: 3061299 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.6356. Min Act: -0.1700
Data Index: 5074203 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19