Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5084 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6566. Min Range: -8.6566
Max Act: 8.6566. Min Act: -0.1700
Data Index: 4791415 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6566. Min Range: -8.6566
Max Act: 8.4066. Min Act: -0.1700
Data Index: 2847748 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6566. Min Range: -8.6566
Max Act: 8.4066. Min Act: -0.1700
Data Index: 8811422 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6566. Min Range: -8.6566
Max Act: 8.3441. Min Act: -0.1700
Data Index: 2983209 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6566. Min Range: -8.6566
Max Act: 8.2191. Min Act: -0.1700
Data Index: 3378520 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6566. Min Range: -8.6566
Max Act: 8.2191. Min Act: -0.1700
Data Index: 5730617 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6566. Min Range: -8.6566
Max Act: 8.0941. Min Act: -0.1700
Data Index: 1670707 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6566. Min Range: -8.6566
Max Act: 8.2191. Min Act: -0.1700
Data Index: 2657201 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6566. Min Range: -8.6566
Max Act: 8.1566. Min Act: -0.1700
Data Index: 2335149 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6566. Min Range: -8.6566
Max Act: 8.0941. Min Act: -0.1700
Data Index: 5248853 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6566. Min Range: -8.6566
Max Act: 8.0941. Min Act: -0.1700
Data Index: 2335150 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6566. Min Range: -8.6566
Max Act: 8.0941. Min Act: -0.1700
Data Index: 8710794 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6566. Min Range: -8.6566
Max Act: 8.0316. Min Act: -0.1700
Data Index: 4287758 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6566. Min Range: -8.6566
Max Act: 7.9691. Min Act: -0.1700
Data Index: 6360726 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6566. Min Range: -8.6566
Max Act: 7.9691. Min Act: -0.1700
Data Index: 4483464 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6566. Min Range: -8.6566
Max Act: 7.9691. Min Act: -0.1700
Data Index: 5388054 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6566. Min Range: -8.6566
Max Act: 7.9691. Min Act: -0.1700
Data Index: 1704593 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6566. Min Range: -8.6566
Max Act: 7.9691. Min Act: -0.1700
Data Index: 5755403 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6566. Min Range: -8.6566
Max Act: 7.9691. Min Act: -0.1700
Data Index: 3281809 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6566. Min Range: -8.6566
Max Act: 7.9691. Min Act: -0.1700
Data Index: 3900090 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19