Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 511 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.5532. Min Range: -5.5532

Max Act: 5.5532. Min Act: -0.0000

Data Index: 442753 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 5.5532. Min Range: -5.5532

Max Act: 5.3078. Min Act: -0.0000

Data Index: 275257 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 5.5532. Min Range: -5.5532

Max Act: 4.8657. Min Act: -0.0000

Data Index: 918250 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 5.5532. Min Range: -5.5532

Max Act: 4.6928. Min Act: -0.0000

Data Index: 56716 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 5.5532. Min Range: -5.5532

Max Act: 4.9067. Min Act: -0.0000

Data Index: 899885 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 5.5532. Min Range: -5.5532

Max Act: 4.9535. Min Act: -0.0000

Data Index: 1200021 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 5.5532. Min Range: -5.5532

Max Act: 4.5356. Min Act: -0.0000

Data Index: 816154 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 5.5532. Min Range: -5.5532

Max Act: 4.4198. Min Act: -0.0000

Data Index: 998512 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 5.5532. Min Range: -5.5532

Max Act: 4.5838. Min Act: -0.0000

Data Index: 370721 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 5.5532. Min Range: -5.5532

Max Act: 4.5157. Min Act: -0.0000

Data Index: 1199551 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 5.5532. Min Range: -5.5532

Max Act: 4.3667. Min Act: -0.0000

Data Index: 1281827 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 5.5532. Min Range: -5.5532

Max Act: 4.5572. Min Act: -0.0000

Data Index: 372180 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 5.5532. Min Range: -5.5532

Max Act: 4.2932. Min Act: -0.0000

Data Index: 734273 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 5.5532. Min Range: -5.5532

Max Act: 4.4843. Min Act: -0.0000

Data Index: 221664 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 5.5532. Min Range: -5.5532

Max Act: 4.4267. Min Act: -0.0000

Data Index: 51339 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 5.5532. Min Range: -5.5532

Max Act: 4.3027. Min Act: -0.0000

Data Index: 933481 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 5.5532. Min Range: -5.5532

Max Act: 4.5298. Min Act: -0.0000

Data Index: 647584 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 5.5532. Min Range: -5.5532

Max Act: 4.1115. Min Act: -0.0000

Data Index: 1258287 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 5.5532. Min Range: -5.5532

Max Act: 4.6502. Min Act: -0.0000

Data Index: 856547 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 5.5532. Min Range: -5.5532

Max Act: 4.5140. Min Act: -0.0000

Data Index: 181283 (C4 (Web Text))

Max Activating Token Index: 271