Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1166 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9245. Min Range: -5.9245
Max Act: 5.9245. Min Act: -0.1700
Data Index: 4893016 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9245. Min Range: -5.9245
Max Act: 5.8933. Min Act: -0.1700
Data Index: 469491 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9245. Min Range: -5.9245
Max Act: 5.8933. Min Act: -0.1700
Data Index: 8026065 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9245. Min Range: -5.9245
Max Act: 5.8620. Min Act: -0.1691
Data Index: 5333477 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9245. Min Range: -5.9245
Max Act: 5.8620. Min Act: -0.1699
Data Index: 4403761 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9245. Min Range: -5.9245
Max Act: 5.8620. Min Act: -0.1700
Data Index: 697096 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9245. Min Range: -5.9245
Max Act: 5.8933. Min Act: -0.1700
Data Index: 1586251 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9245. Min Range: -5.9245
Max Act: 5.8620. Min Act: -0.1700
Data Index: 8256310 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9245. Min Range: -5.9245
Max Act: 5.8620. Min Act: -0.1700
Data Index: 5263842 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9245. Min Range: -5.9245
Max Act: 5.8620. Min Act: -0.1700
Data Index: 6852407 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9245. Min Range: -5.9245
Max Act: 5.8308. Min Act: -0.1700
Data Index: 404919 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9245. Min Range: -5.9245
Max Act: 5.8308. Min Act: -0.1700
Data Index: 4934713 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9245. Min Range: -5.9245
Max Act: 5.8308. Min Act: -0.1699
Data Index: 1052231 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9245. Min Range: -5.9245
Max Act: 5.8308. Min Act: -0.1700
Data Index: 2680503 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9245. Min Range: -5.9245
Max Act: 5.8308. Min Act: -0.1700
Data Index: 6436139 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9245. Min Range: -5.9245
Max Act: 5.8308. Min Act: -0.1700
Data Index: 4683778 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9245. Min Range: -5.9245
Max Act: 5.8308. Min Act: -0.1700
Data Index: 2630723 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9245. Min Range: -5.9245
Max Act: 5.7995. Min Act: -0.1700
Data Index: 1480713 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9245. Min Range: -5.9245
Max Act: 5.7995. Min Act: -0.1700
Data Index: 5436169 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9245. Min Range: -5.9245
Max Act: 5.7995. Min Act: -0.1700
Data Index: 5969655 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19