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

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

Neuron 2816 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.4483. Min Act: -0.0002

Data Index: 44053 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3465. Min Act: -0.0002

Data Index: 114798 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3141. Min Act: -0.0002

Data Index: 536290 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.2669. Min Act: -0.0002

Data Index: 407195 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.2515. Min Act: -0.0002

Data Index: 808555 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.2477. Min Act: -0.0002

Data Index: 1262946 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.2494. Min Act: -0.0002

Data Index: 661321 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.2297. Min Act: -0.0002

Data Index: 1166123 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.2448. Min Act: -0.0002

Data Index: 236720 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.2364. Min Act: -0.0002

Data Index: 330015 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.2492. Min Act: -0.0002

Data Index: 1236339 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.2443. Min Act: -0.0002

Data Index: 520603 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.2330. Min Act: -0.0002

Data Index: 847435 (C4 (Web Text))

Max Activating Token Index: 861

Text #13

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.2311. Min Act: -0.0002

Data Index: 262924 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.2302. Min Act: -0.0002

Data Index: 747107 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.2252. Min Act: -0.0002

Data Index: 418867 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.2323. Min Act: -0.0002

Data Index: 34157 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.2163. Min Act: -0.0002

Data Index: 767630 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.2294. Min Act: -0.0002

Data Index: 1163782 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.2359. Min Act: -0.0002

Data Index: 1137904 (C4 (Web Text))

Max Activating Token Index: 268