Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2084 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.4282. Min Act: -0.0001

Data Index: 22825 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.2995. Min Act: -0.0001

Data Index: 271945 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.3322. Min Act: -0.0001

Data Index: 244277 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.3319. Min Act: -0.0001

Data Index: 1166560 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.2693. Min Act: -0.0001

Data Index: 456780 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.0784. Min Act: -0.0001

Data Index: 1356596 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.0788. Min Act: -0.0001

Data Index: 1144473 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.1035. Min Act: -0.0001

Data Index: 1226376 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 1.4282. Min Range: -1.4282

Max Act: 0.9396. Min Act: -0.0001

Data Index: 319102 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.0249. Min Act: -0.0001

Data Index: 700919 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.0441. Min Act: -0.0001

Data Index: 511269 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.0367. Min Act: -0.0001

Data Index: 1210625 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.0301. Min Act: -0.0001

Data Index: 1024401 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.0195. Min Act: -0.0001

Data Index: 514832 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 1.4282. Min Range: -1.4282

Max Act: 0.9016. Min Act: -0.0001

Data Index: 916076 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 1.4282. Min Range: -1.4282

Max Act: 0.9903. Min Act: -0.0001

Data Index: 836296 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 1.4282. Min Range: -1.4282

Max Act: 0.8860. Min Act: -0.0001

Data Index: 410795 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.0040. Min Act: -0.0001

Data Index: 908634 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 1.4282. Min Range: -1.4282

Max Act: 0.9660. Min Act: -0.0001

Data Index: 534420 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 1.4282. Min Range: -1.4282

Max Act: 0.9065. Min Act: -0.0001

Data Index: 702204 (C4 (Web Text))

Max Activating Token Index: 58