Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3724 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0646. Min Range: -7.0646
Max Act: 7.0646. Min Act: -0.1700
Data Index: 1552626 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0646. Min Range: -7.0646
Max Act: 6.9709. Min Act: -0.1700
Data Index: 8180738 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0646. Min Range: -7.0646
Max Act: 6.9709. Min Act: -0.1700
Data Index: 5176428 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0646. Min Range: -7.0646
Max Act: 6.9709. Min Act: -0.1700
Data Index: 5936840 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0646. Min Range: -7.0646
Max Act: 6.9396. Min Act: -0.1700
Data Index: 8221863 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0646. Min Range: -7.0646
Max Act: 6.9396. Min Act: -0.1700
Data Index: 4556684 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0646. Min Range: -7.0646
Max Act: 6.8459. Min Act: -0.1700
Data Index: 1421535 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0646. Min Range: -7.0646
Max Act: 6.8146. Min Act: -0.1700
Data Index: 867628 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0646. Min Range: -7.0646
Max Act: 6.8146. Min Act: -0.1700
Data Index: 6033929 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0646. Min Range: -7.0646
Max Act: 6.7834. Min Act: -0.1700
Data Index: 7221999 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0646. Min Range: -7.0646
Max Act: 6.7209. Min Act: -0.1700
Data Index: 6568322 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0646. Min Range: -7.0646
Max Act: 6.7209. Min Act: -0.1700
Data Index: 7833369 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0646. Min Range: -7.0646
Max Act: 6.6896. Min Act: -0.1700
Data Index: 7881321 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0646. Min Range: -7.0646
Max Act: 6.6896. Min Act: -0.1700
Data Index: 527285 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0646. Min Range: -7.0646
Max Act: 6.6271. Min Act: -0.1700
Data Index: 2256042 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0646. Min Range: -7.0646
Max Act: 6.5959. Min Act: -0.1700
Data Index: 334589 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0646. Min Range: -7.0646
Max Act: 6.5646. Min Act: -0.1700
Data Index: 6768666 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0646. Min Range: -7.0646
Max Act: 6.5646. Min Act: -0.1700
Data Index: 6335218 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0646. Min Range: -7.0646
Max Act: 6.5334. Min Act: -0.1700
Data Index: 7400287 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0646. Min Range: -7.0646
Max Act: 6.5334. Min Act: -0.1700
Data Index: 1824679 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19