Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 138 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.6529. Min Range: -0.6529
Max Act: 0.6529. Min Act: -0.0001
Data Index: 443812 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6529. Min Range: -0.6529
Max Act: 0.6449. Min Act: -0.0001
Data Index: 24233 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6529. Min Range: -0.6529
Max Act: 0.6342. Min Act: -0.0001
Data Index: 491423 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6529. Min Range: -0.6529
Max Act: 0.6327. Min Act: -0.0001
Data Index: 622927 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6529. Min Range: -0.6529
Max Act: 0.6292. Min Act: -0.0001
Data Index: 1290378 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6529. Min Range: -0.6529
Max Act: 0.6196. Min Act: -0.0001
Data Index: 190178 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6529. Min Range: -0.6529
Max Act: 0.6111. Min Act: -0.0001
Data Index: 782427 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6529. Min Range: -0.6529
Max Act: 0.5988. Min Act: -0.0001
Data Index: 18554 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6529. Min Range: -0.6529
Max Act: 0.5985. Min Act: -0.0001
Data Index: 932642 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6529. Min Range: -0.6529
Max Act: 0.5783. Min Act: -0.0001
Data Index: 1318356 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6529. Min Range: -0.6529
Max Act: 0.5872. Min Act: -0.0001
Data Index: 956425 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6529. Min Range: -0.6529
Max Act: 0.6032. Min Act: -0.0001
Data Index: 1530960 (Python Code)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6529. Min Range: -0.6529
Max Act: 0.5908. Min Act: -0.0001
Data Index: 792662 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6529. Min Range: -0.6529
Max Act: 0.5502. Min Act: -0.0001
Data Index: 904620 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6529. Min Range: -0.6529
Max Act: 0.5710. Min Act: -0.0001
Data Index: 294451 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6529. Min Range: -0.6529
Max Act: 0.5879. Min Act: -0.0001
Data Index: 744678 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6529. Min Range: -0.6529
Max Act: 0.5819. Min Act: -0.0001
Data Index: 1625196 (Python Code)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6529. Min Range: -0.6529
Max Act: 0.5381. Min Act: -0.0001
Data Index: 271670 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6529. Min Range: -0.6529
Max Act: 0.5736. Min Act: -0.0001
Data Index: 344017 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6529. Min Range: -0.6529
Max Act: 0.5750. Min Act: -0.0001
Data Index: 918186 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19