Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 230 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1663. Min Range: -5.1663
Max Act: 5.1663. Min Act: -0.1700
Data Index: 7866147 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1663. Min Range: -5.1663
Max Act: 5.0725. Min Act: -0.1700
Data Index: 7617364 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1663. Min Range: -5.1663
Max Act: 5.0725. Min Act: -0.1700
Data Index: 333129 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1663. Min Range: -5.1663
Max Act: 5.0725. Min Act: -0.1700
Data Index: 6274804 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1663. Min Range: -5.1663
Max Act: 5.0413. Min Act: -0.1700
Data Index: 3865171 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1663. Min Range: -5.1663
Max Act: 5.0413. Min Act: -0.1700
Data Index: 2077812 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1663. Min Range: -5.1663
Max Act: 5.0100. Min Act: -0.1700
Data Index: 8103072 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1663. Min Range: -5.1663
Max Act: 5.0100. Min Act: -0.1700
Data Index: 7379778 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.9788. Min Act: -0.1700
Data Index: 8341086 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.9475. Min Act: -0.1700
Data Index: 4698116 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.9475. Min Act: -0.1700
Data Index: 3609521 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.9475. Min Act: -0.1700
Data Index: 3451645 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.9475. Min Act: -0.1700
Data Index: 1424895 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.9163. Min Act: -0.1700
Data Index: 2013098 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.9163. Min Act: -0.1700
Data Index: 6377408 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.9163. Min Act: -0.1700
Data Index: 5855413 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.8850. Min Act: -0.1700
Data Index: 3966872 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.8850. Min Act: -0.1700
Data Index: 6961973 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.9163. Min Act: -0.1700
Data Index: 3656337 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1663. Min Range: -5.1663
Max Act: 4.8850. Min Act: -0.1700
Data Index: 3522988 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19