Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3558 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8359. Min Range: -5.8359
Max Act: 5.8359. Min Act: -0.1700
Data Index: 5097524 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8359. Min Range: -5.8359
Max Act: 5.7734. Min Act: -0.1700
Data Index: 7300950 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8359. Min Range: -5.8359
Max Act: 5.7421. Min Act: -0.1700
Data Index: 5230595 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8359. Min Range: -5.8359
Max Act: 5.6796. Min Act: -0.1700
Data Index: 8258704 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8359. Min Range: -5.8359
Max Act: 5.6171. Min Act: -0.1700
Data Index: 6399010 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8359. Min Range: -5.8359
Max Act: 5.6484. Min Act: -0.1700
Data Index: 5775170 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8359. Min Range: -5.8359
Max Act: 5.6484. Min Act: -0.1700
Data Index: 5069892 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8359. Min Range: -5.8359
Max Act: 5.6484. Min Act: -0.1700
Data Index: 4777836 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8359. Min Range: -5.8359
Max Act: 5.6484. Min Act: -0.1700
Data Index: 6764583 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8359. Min Range: -5.8359
Max Act: 5.6171. Min Act: -0.1700
Data Index: 7202744 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8359. Min Range: -5.8359
Max Act: 5.5859. Min Act: -0.1700
Data Index: 3340173 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8359. Min Range: -5.8359
Max Act: 5.5859. Min Act: -0.1700
Data Index: 7590792 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8359. Min Range: -5.8359
Max Act: 5.5859. Min Act: -0.1700
Data Index: 6359973 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8359. Min Range: -5.8359
Max Act: 5.5546. Min Act: -0.1700
Data Index: 7714079 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8359. Min Range: -5.8359
Max Act: 5.5546. Min Act: -0.1700
Data Index: 767936 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8359. Min Range: -5.8359
Max Act: 5.5546. Min Act: -0.1700
Data Index: 643284 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8359. Min Range: -5.8359
Max Act: 5.5234. Min Act: -0.1700
Data Index: 1442015 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8359. Min Range: -5.8359
Max Act: 5.5234. Min Act: -0.1700
Data Index: 2276871 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8359. Min Range: -5.8359
Max Act: 5.5234. Min Act: -0.1700
Data Index: 7279588 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8359. Min Range: -5.8359
Max Act: 5.5234. Min Act: -0.1700
Data Index: 3205427 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19