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

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

Neuron 1168 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.3528. Min Act: -0.0000

Data Index: 729442 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.3158. Min Act: -0.0000

Data Index: 1111616 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.3209. Min Act: -0.0000

Data Index: 370032 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.3040. Min Act: -0.0000

Data Index: 1150921 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.3303. Min Act: -0.0000

Data Index: 393269 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.2920. Min Act: -0.0000

Data Index: 39798 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.3431. Min Act: -0.0000

Data Index: 670692 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.3134. Min Act: -0.0000

Data Index: 665045 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.3002. Min Act: -0.0000

Data Index: 1237582 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.2916. Min Act: -0.0001

Data Index: 232912 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.2727. Min Act: -0.0001

Data Index: 551199 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.2725. Min Act: -0.0000

Data Index: 680641 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.2879. Min Act: -0.0000

Data Index: 632208 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.2866. Min Act: -0.0000

Data Index: 592063 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.2862. Min Act: -0.0001

Data Index: 1070831 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.2727. Min Act: -0.0000

Data Index: 562367 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.2638. Min Act: -0.0000

Data Index: 193275 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.2798. Min Act: -0.0000

Data Index: 297062 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.2695. Min Act: -0.0000

Data Index: 226120 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 0.3528. Min Range: -0.3528

Max Act: 0.2570. Min Act: -0.0000

Data Index: 148966 (C4 (Web Text))

Max Activating Token Index: 876