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

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

Neuron 886 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.7771. Min Act: -0.0001

Data Index: 322501 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.3511. Min Act: -0.0001

Data Index: 976322 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.3386. Min Act: -0.0001

Data Index: 460072 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.4522. Min Act: -0.0001

Data Index: 908237 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.3316. Min Act: -0.0001

Data Index: 443568 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.2977. Min Act: -0.0001

Data Index: 1202591 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.3198. Min Act: -0.0001

Data Index: 204167 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.3308. Min Act: -0.0001

Data Index: 562097 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.2513. Min Act: -0.0001

Data Index: 195592 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.2659. Min Act: -0.0001

Data Index: 805098 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.2354. Min Act: -0.0001

Data Index: 841804 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.2186. Min Act: -0.0001

Data Index: 1011475 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.2484. Min Act: -0.0001

Data Index: 142014 (C4 (Web Text))

Max Activating Token Index: 891

Text #13

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.1927. Min Act: -0.0001

Data Index: 268792 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.0628. Min Act: -0.0001

Data Index: 745162 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.1370. Min Act: -0.0001

Data Index: 733159 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.1183. Min Act: -0.0001

Data Index: 1270587 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.1171. Min Act: -0.0001

Data Index: 931350 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.0378. Min Act: -0.0001

Data Index: 646902 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 1.7771. Min Range: -1.7771

Max Act: 1.0553. Min Act: -0.0001

Data Index: 213779 (C4 (Web Text))

Max Activating Token Index: 88