Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4849 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9350. Min Range: -3.9350
Max Act: 3.9350. Min Act: -0.1700
Data Index: 3683730 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9350. Min Range: -3.9350
Max Act: 3.9037. Min Act: -0.1700
Data Index: 5210013 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9350. Min Range: -3.9350
Max Act: 3.8725. Min Act: -0.1700
Data Index: 5144507 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9350. Min Range: -3.9350
Max Act: 3.8412. Min Act: -0.1700
Data Index: 8784872 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9350. Min Range: -3.9350
Max Act: 3.8412. Min Act: -0.1700
Data Index: 4857524 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9350. Min Range: -3.9350
Max Act: 3.7943. Min Act: -0.1700
Data Index: 4964443 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9350. Min Range: -3.9350
Max Act: 3.7630. Min Act: -0.1700
Data Index: 8772815 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9350. Min Range: -3.9350
Max Act: 3.7787. Min Act: -0.1700
Data Index: 4401178 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9350. Min Range: -3.9350
Max Act: 3.7474. Min Act: -0.1700
Data Index: 8344999 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9350. Min Range: -3.9350
Max Act: 3.7317. Min Act: -0.1700
Data Index: 7259744 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9350. Min Range: -3.9350
Max Act: 3.7317. Min Act: -0.1700
Data Index: 633065 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9350. Min Range: -3.9350
Max Act: 3.7005. Min Act: -0.1700
Data Index: 5519583 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9350. Min Range: -3.9350
Max Act: 3.7161. Min Act: -0.1700
Data Index: 4727643 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9350. Min Range: -3.9350
Max Act: 3.7161. Min Act: -0.1700
Data Index: 2821177 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9350. Min Range: -3.9350
Max Act: 3.7005. Min Act: -0.1700
Data Index: 3979391 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9350. Min Range: -3.9350
Max Act: 3.7005. Min Act: -0.1700
Data Index: 1613706 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9350. Min Range: -3.9350
Max Act: 3.6848. Min Act: -0.1700
Data Index: 3005515 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9350. Min Range: -3.9350
Max Act: 3.6692. Min Act: -0.1700
Data Index: 7159302 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9350. Min Range: -3.9350
Max Act: 3.6692. Min Act: -0.1700
Data Index: 5327776 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9350. Min Range: -3.9350
Max Act: 3.6692. Min Act: -0.1700
Data Index: 4312877 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19