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

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

Neuron 3423 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0434. Min Range: -5.0434

Max Act: 5.0434. Min Act: -0.0000

Data Index: 866853 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 5.0434. Min Range: -5.0434

Max Act: 4.4203. Min Act: -0.0000

Data Index: 845877 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 5.0434. Min Range: -5.0434

Max Act: 4.4790. Min Act: -0.0000

Data Index: 310683 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 5.0434. Min Range: -5.0434

Max Act: 3.7784. Min Act: -0.0000

Data Index: 759436 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 5.0434. Min Range: -5.0434

Max Act: 3.3770. Min Act: -0.0000

Data Index: 1201088 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 5.0434. Min Range: -5.0434

Max Act: 3.4772. Min Act: -0.0000

Data Index: 1348481 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 5.0434. Min Range: -5.0434

Max Act: 3.2686. Min Act: -0.0000

Data Index: 1277654 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 5.0434. Min Range: -5.0434

Max Act: 3.4135. Min Act: -0.0000

Data Index: 1340448 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 5.0434. Min Range: -5.0434

Max Act: 3.5153. Min Act: -0.0000

Data Index: 404974 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 5.0434. Min Range: -5.0434

Max Act: 3.2485. Min Act: -0.0000

Data Index: 586427 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 5.0434. Min Range: -5.0434

Max Act: 3.2119. Min Act: -0.0000

Data Index: 1146248 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 5.0434. Min Range: -5.0434

Max Act: 3.3450. Min Act: -0.0000

Data Index: 80218 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 5.0434. Min Range: -5.0434

Max Act: 3.1766. Min Act: -0.0000

Data Index: 1131424 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 5.0434. Min Range: -5.0434

Max Act: 3.3162. Min Act: -0.0000

Data Index: 1293637 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 5.0434. Min Range: -5.0434

Max Act: 3.1279. Min Act: -0.0000

Data Index: 650511 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 5.0434. Min Range: -5.0434

Max Act: 3.1094. Min Act: -0.0000

Data Index: 160988 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 5.0434. Min Range: -5.0434

Max Act: 2.9311. Min Act: -0.0000

Data Index: 40882 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 5.0434. Min Range: -5.0434

Max Act: 3.0420. Min Act: -0.0000

Data Index: 476137 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 5.0434. Min Range: -5.0434

Max Act: 3.0307. Min Act: -0.0000

Data Index: 12924 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 5.0434. Min Range: -5.0434

Max Act: 2.7373. Min Act: -0.0000

Data Index: 668452 (C4 (Web Text))

Max Activating Token Index: 782