Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 340 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2992. Min Act: -0.0003

Data Index: 1281074 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2824. Min Act: -0.0003

Data Index: 871698 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2549. Min Act: -0.0003

Data Index: 251953 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2636. Min Act: -0.0003

Data Index: 684529 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2550. Min Act: -0.0003

Data Index: 1056189 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2380. Min Act: -0.0003

Data Index: 1038714 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2538. Min Act: -0.0003

Data Index: 653649 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2316. Min Act: -0.0003

Data Index: 632199 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2723. Min Act: -0.0003

Data Index: 1250127 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2373. Min Act: -0.0003

Data Index: 816304 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2342. Min Act: -0.0003

Data Index: 472508 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2272. Min Act: -0.0003

Data Index: 1132091 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2360. Min Act: -0.0003

Data Index: 146193 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2241. Min Act: -0.0003

Data Index: 394364 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2241. Min Act: -0.0003

Data Index: 94355 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2132. Min Act: -0.0003

Data Index: 141051 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2241. Min Act: -0.0003

Data Index: 727983 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2466. Min Act: -0.0003

Data Index: 210386 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2343. Min Act: -0.0003

Data Index: 642004 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2173. Min Act: -0.0003

Data Index: 1108376 (C4 (Web Text))

Max Activating Token Index: 35