Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3540 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8535. Min Range: -5.8535
Max Act: 5.8535. Min Act: -0.1700
Data Index: 2505074 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8535. Min Range: -5.8535
Max Act: 5.8222. Min Act: -0.1700
Data Index: 4371854 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8535. Min Range: -5.8535
Max Act: 5.7597. Min Act: -0.1700
Data Index: 3191523 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8535. Min Range: -5.8535
Max Act: 5.7597. Min Act: -0.1700
Data Index: 4645470 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8535. Min Range: -5.8535
Max Act: 5.7285. Min Act: -0.1700
Data Index: 6252791 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8535. Min Range: -5.8535
Max Act: 5.6660. Min Act: -0.1700
Data Index: 1773065 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8535. Min Range: -5.8535
Max Act: 5.6347. Min Act: -0.1700
Data Index: 4023717 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8535. Min Range: -5.8535
Max Act: 5.6347. Min Act: -0.1700
Data Index: 1727724 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8535. Min Range: -5.8535
Max Act: 5.5722. Min Act: -0.1700
Data Index: 8003049 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8535. Min Range: -5.8535
Max Act: 5.5722. Min Act: -0.1700
Data Index: 3701642 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8535. Min Range: -5.8535
Max Act: 5.5722. Min Act: -0.1700
Data Index: 111892 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8535. Min Range: -5.8535
Max Act: 5.5722. Min Act: -0.1700
Data Index: 5970080 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8535. Min Range: -5.8535
Max Act: 5.5722. Min Act: -0.1700
Data Index: 4317710 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8535. Min Range: -5.8535
Max Act: 5.5410. Min Act: -0.1700
Data Index: 7358031 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8535. Min Range: -5.8535
Max Act: 5.5410. Min Act: -0.1700
Data Index: 6003364 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8535. Min Range: -5.8535
Max Act: 5.5410. Min Act: -0.1700
Data Index: 6581912 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8535. Min Range: -5.8535
Max Act: 5.5410. Min Act: -0.1700
Data Index: 4957101 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8535. Min Range: -5.8535
Max Act: 5.5097. Min Act: -0.1700
Data Index: 8203201 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8535. Min Range: -5.8535
Max Act: 5.4785. Min Act: -0.1700
Data Index: 5744269 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8535. Min Range: -5.8535
Max Act: 5.4785. Min Act: -0.1700
Data Index: 313147 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19