Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3625 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1678. Min Range: -7.1678
Max Act: 7.1678. Min Act: -0.1700
Data Index: 3238914 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1678. Min Range: -7.1678
Max Act: 7.0740. Min Act: -0.1700
Data Index: 5412689 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1678. Min Range: -7.1678
Max Act: 6.9490. Min Act: -0.1700
Data Index: 7977644 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1678. Min Range: -7.1678
Max Act: 6.9178. Min Act: -0.1700
Data Index: 7643878 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1678. Min Range: -7.1678
Max Act: 6.8865. Min Act: -0.1700
Data Index: 8336557 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1678. Min Range: -7.1678
Max Act: 6.8553. Min Act: -0.1700
Data Index: 205110 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1678. Min Range: -7.1678
Max Act: 6.7615. Min Act: -0.1700
Data Index: 5025758 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1678. Min Range: -7.1678
Max Act: 6.7303. Min Act: -0.1700
Data Index: 2317845 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1678. Min Range: -7.1678
Max Act: 6.7303. Min Act: -0.1700
Data Index: 8145091 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1678. Min Range: -7.1678
Max Act: 6.7303. Min Act: -0.1700
Data Index: 4642249 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1678. Min Range: -7.1678
Max Act: 6.6990. Min Act: -0.1700
Data Index: 4669035 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1678. Min Range: -7.1678
Max Act: 6.6990. Min Act: -0.1700
Data Index: 18700 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1678. Min Range: -7.1678
Max Act: 6.6990. Min Act: -0.1700
Data Index: 766545 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1678. Min Range: -7.1678
Max Act: 6.6990. Min Act: -0.1700
Data Index: 2242001 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1678. Min Range: -7.1678
Max Act: 6.6678. Min Act: -0.1700
Data Index: 8510437 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1678. Min Range: -7.1678
Max Act: 6.6990. Min Act: -0.1700
Data Index: 4669036 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1678. Min Range: -7.1678
Max Act: 6.6365. Min Act: -0.1700
Data Index: 8131780 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1678. Min Range: -7.1678
Max Act: 6.6365. Min Act: -0.1700
Data Index: 1915360 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1678. Min Range: -7.1678
Max Act: 6.6365. Min Act: -0.1700
Data Index: 5908031 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1678. Min Range: -7.1678
Max Act: 6.6053. Min Act: -0.1700
Data Index: 7054132 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19