Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5189 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2104. Min Range: -5.2104
Max Act: 5.2104. Min Act: -0.1700
Data Index: 7946430 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2104. Min Range: -5.2104
Max Act: 5.1792. Min Act: -0.1700
Data Index: 6804738 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2104. Min Range: -5.2104
Max Act: 5.1167. Min Act: -0.1700
Data Index: 3299617 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2104. Min Range: -5.2104
Max Act: 5.1167. Min Act: -0.1700
Data Index: 390761 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2104. Min Range: -5.2104
Max Act: 5.0854. Min Act: -0.1700
Data Index: 3299614 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2104. Min Range: -5.2104
Max Act: 5.0854. Min Act: -0.1700
Data Index: 6305420 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2104. Min Range: -5.2104
Max Act: 5.0542. Min Act: -0.1700
Data Index: 4213 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2104. Min Range: -5.2104
Max Act: 5.0542. Min Act: -0.1700
Data Index: 3023853 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2104. Min Range: -5.2104
Max Act: 5.0542. Min Act: -0.1700
Data Index: 5079865 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2104. Min Range: -5.2104
Max Act: 5.0229. Min Act: -0.1700
Data Index: 6594415 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2104. Min Range: -5.2104
Max Act: 5.0229. Min Act: -0.1700
Data Index: 2802856 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2104. Min Range: -5.2104
Max Act: 5.0229. Min Act: -0.1700
Data Index: 4077250 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2104. Min Range: -5.2104
Max Act: 5.0229. Min Act: -0.1700
Data Index: 7033321 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2104. Min Range: -5.2104
Max Act: 5.0229. Min Act: -0.1700
Data Index: 8580368 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2104. Min Range: -5.2104
Max Act: 4.9917. Min Act: -0.1700
Data Index: 390762 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2104. Min Range: -5.2104
Max Act: 4.9917. Min Act: -0.1700
Data Index: 3322232 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2104. Min Range: -5.2104
Max Act: 4.9917. Min Act: -0.1700
Data Index: 4047272 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2104. Min Range: -5.2104
Max Act: 4.9917. Min Act: -0.1700
Data Index: 5483092 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2104. Min Range: -5.2104
Max Act: 4.9917. Min Act: -0.1700
Data Index: 2275735 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2104. Min Range: -5.2104
Max Act: 4.9917. Min Act: -0.1700
Data Index: 4565521 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19