Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 205 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2663. Min Range: -3.2663
Max Act: 3.2663. Min Act: -0.1700
Data Index: 5631466 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2663. Min Range: -3.2663
Max Act: 3.2506. Min Act: -0.1700
Data Index: 962871 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2663. Min Range: -3.2663
Max Act: 3.2192. Min Act: -0.1700
Data Index: 2683767 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2663. Min Range: -3.2663
Max Act: 3.2192. Min Act: -0.1700
Data Index: 3506772 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2663. Min Range: -3.2663
Max Act: 3.2192. Min Act: -0.1700
Data Index: 6087045 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2663. Min Range: -3.2663
Max Act: 3.1877. Min Act: -0.1700
Data Index: 7406888 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2663. Min Range: -3.2663
Max Act: 3.2035. Min Act: -0.1700
Data Index: 566305 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2663. Min Range: -3.2663
Max Act: 3.2035. Min Act: -0.1700
Data Index: 5870165 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2663. Min Range: -3.2663
Max Act: 3.1877. Min Act: -0.1700
Data Index: 1697443 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2663. Min Range: -3.2663
Max Act: 3.2035. Min Act: -0.1700
Data Index: 7171286 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2663. Min Range: -3.2663
Max Act: 3.1720. Min Act: -0.1700
Data Index: 8555553 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2663. Min Range: -3.2663
Max Act: 3.1720. Min Act: -0.1700
Data Index: 5312851 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2663. Min Range: -3.2663
Max Act: 3.1405. Min Act: -0.1700
Data Index: 182450 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2663. Min Range: -3.2663
Max Act: 3.1405. Min Act: -0.1700
Data Index: 1487446 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2663. Min Range: -3.2663
Max Act: 3.1563. Min Act: -0.1700
Data Index: 52436 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2663. Min Range: -3.2663
Max Act: 3.1563. Min Act: -0.1700
Data Index: 4880753 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2663. Min Range: -3.2663
Max Act: 3.1405. Min Act: -0.1700
Data Index: 152462 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2663. Min Range: -3.2663
Max Act: 3.1248. Min Act: -0.1700
Data Index: 3335088 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2663. Min Range: -3.2663
Max Act: 3.1563. Min Act: -0.1700
Data Index: 654441 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2663. Min Range: -3.2663
Max Act: 3.1248. Min Act: -0.1700
Data Index: 2254481 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19