Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4325 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.7244. Min Act: -0.0000

Data Index: 899704 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.6660. Min Act: -0.0000

Data Index: 170466 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.5688. Min Act: -0.0000

Data Index: 596368 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.5504. Min Act: -0.0000

Data Index: 151824 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.5869. Min Act: -0.0000

Data Index: 1203687 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.5488. Min Act: -0.0000

Data Index: 1317215 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.5795. Min Act: -0.0000

Data Index: 898644 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.5801. Min Act: -0.0000

Data Index: 849160 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.5532. Min Act: -0.0000

Data Index: 606173 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.5693. Min Act: -0.0001

Data Index: 1108976 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.5147. Min Act: -0.0000

Data Index: 916943 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.5316. Min Act: -0.0000

Data Index: 1290352 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.4970. Min Act: -0.0000

Data Index: 962956 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.4773. Min Act: -0.0000

Data Index: 707717 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.4805. Min Act: -0.0000

Data Index: 657360 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.4485. Min Act: -0.0000

Data Index: 1128396 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.5001. Min Act: -0.0000

Data Index: 575916 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.4868. Min Act: -0.0000

Data Index: 942731 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.4664. Min Act: -0.0000

Data Index: 1217431 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 0.7244. Min Range: -0.7244

Max Act: 0.4655. Min Act: -0.0000

Data Index: 383828 (C4 (Web Text))

Max Activating Token Index: 655