Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3343 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7555. Min Range: -2.7555
Max Act: 2.7555. Min Act: -0.1700
Data Index: 4479365 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7555. Min Range: -2.7555
Max Act: 2.7555. Min Act: -0.1700
Data Index: 3552276 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7555. Min Range: -2.7555
Max Act: 2.7555. Min Act: -0.1700
Data Index: 2315596 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7555. Min Range: -2.7555
Max Act: 2.7555. Min Act: -0.1700
Data Index: 2774054 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7555. Min Range: -2.7555
Max Act: 2.7555. Min Act: -0.1700
Data Index: 8766303 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7555. Min Range: -2.7555
Max Act: 2.7555. Min Act: -0.1700
Data Index: 2711100 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7555. Min Range: -2.7555
Max Act: 2.7236. Min Act: -0.1700
Data Index: 3418143 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7555. Min Range: -2.7555
Max Act: 2.7236. Min Act: -0.1700
Data Index: 583712 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7555. Min Range: -2.7555
Max Act: 2.6756. Min Act: -0.1700
Data Index: 1610850 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7555. Min Range: -2.7555
Max Act: 2.6114. Min Act: -0.1700
Data Index: 3060116 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7555. Min Range: -2.7555
Max Act: 2.6114. Min Act: -0.1700
Data Index: 2578276 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7555. Min Range: -2.7555
Max Act: 2.6114. Min Act: -0.1700
Data Index: 2130739 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7555. Min Range: -2.7555
Max Act: 2.6114. Min Act: -0.1700
Data Index: 4998778 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7555. Min Range: -2.7555
Max Act: 2.5630. Min Act: -0.1700
Data Index: 3143407 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7555. Min Range: -2.7555
Max Act: 2.5630. Min Act: -0.1700
Data Index: 3053644 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7555. Min Range: -2.7555
Max Act: 2.5630. Min Act: -0.1700
Data Index: 2469694 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7555. Min Range: -2.7555
Max Act: 2.5630. Min Act: -0.1700
Data Index: 2981494 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7555. Min Range: -2.7555
Max Act: 2.5630. Min Act: -0.1700
Data Index: 2816437 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7555. Min Range: -2.7555
Max Act: 2.5630. Min Act: -0.1700
Data Index: 2638680 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7555. Min Range: -2.7555
Max Act: 2.5630. Min Act: -0.1700
Data Index: 4290493 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19