Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2657 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2663. Min Range: -4.2663
Max Act: 4.2663. Min Act: -0.1700
Data Index: 8413237 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2663. Min Range: -4.2663
Max Act: 4.2038. Min Act: -0.1700
Data Index: 188281 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2663. Min Range: -4.2663
Max Act: 4.2038. Min Act: -0.1700
Data Index: 984190 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2663. Min Range: -4.2663
Max Act: 4.1725. Min Act: -0.1700
Data Index: 3118012 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2663. Min Range: -4.2663
Max Act: 4.1725. Min Act: -0.1700
Data Index: 1631952 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2663. Min Range: -4.2663
Max Act: 4.1725. Min Act: -0.1700
Data Index: 3747500 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2663. Min Range: -4.2663
Max Act: 4.1412. Min Act: -0.1700
Data Index: 6552662 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2663. Min Range: -4.2663
Max Act: 4.1100. Min Act: -0.1700
Data Index: 7750491 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2663. Min Range: -4.2663
Max Act: 4.1100. Min Act: -0.1700
Data Index: 431902 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2663. Min Range: -4.2663
Max Act: 4.1100. Min Act: -0.1700
Data Index: 8195362 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2663. Min Range: -4.2663
Max Act: 4.0787. Min Act: -0.1700
Data Index: 3677719 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2663. Min Range: -4.2663
Max Act: 4.0787. Min Act: -0.1700
Data Index: 7514737 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2663. Min Range: -4.2663
Max Act: 4.0787. Min Act: -0.1700
Data Index: 3872118 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2663. Min Range: -4.2663
Max Act: 4.0787. Min Act: -0.1700
Data Index: 1246296 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2663. Min Range: -4.2663
Max Act: 4.0787. Min Act: -0.1700
Data Index: 1041951 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2663. Min Range: -4.2663
Max Act: 4.0475. Min Act: -0.1700
Data Index: 5338610 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2663. Min Range: -4.2663
Max Act: 4.0787. Min Act: -0.1700
Data Index: 3897415 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2663. Min Range: -4.2663
Max Act: 4.0475. Min Act: -0.1700
Data Index: 4580595 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2663. Min Range: -4.2663
Max Act: 4.0162. Min Act: -0.1700
Data Index: 4582021 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2663. Min Range: -4.2663
Max Act: 4.0162. Min Act: -0.1700
Data Index: 5293110 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19