Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2641 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.8573. Min Act: -0.1700
Data Index: 5850681 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.8573. Min Act: -0.1700
Data Index: 4518646 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.8573. Min Act: -0.1700
Data Index: 2668849 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.8573. Min Act: -0.1700
Data Index: 17619 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.8260. Min Act: -0.1700
Data Index: 7344334 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.8260. Min Act: -0.1700
Data Index: 7635327 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.7948. Min Act: -0.1700
Data Index: 1233189 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.8260. Min Act: -0.1700
Data Index: 8193395 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.8260. Min Act: -0.1700
Data Index: 574095 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.8260. Min Act: -0.1700
Data Index: 1036504 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.8260. Min Act: -0.1700
Data Index: 7325972 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.8260. Min Act: -0.1700
Data Index: 2892357 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.8260. Min Act: -0.1700
Data Index: 8388991 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.8260. Min Act: -0.1700
Data Index: 5368157 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.8260. Min Act: -0.1700
Data Index: 4842636 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.8260. Min Act: -0.1700
Data Index: 4842637 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.7948. Min Act: -0.1700
Data Index: 3201152 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.7948. Min Act: -0.1700
Data Index: 1719826 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.7948. Min Act: -0.1700
Data Index: 4846870 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.7948. Min Act: -0.1700
Data Index: 5026767 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19