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

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

Neuron 982 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: 1.4931. Min Range: -1.4931

Max Act: 1.4931. Min Act: -0.0001

Data Index: 1134961 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.4280. Min Act: -0.0001

Data Index: 202847 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.3676. Min Act: -0.0000

Data Index: 72797 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.3983. Min Act: -0.0001

Data Index: 420359 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.3380. Min Act: -0.0001

Data Index: 1185026 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.3369. Min Act: -0.0001

Data Index: 1074196 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.3200. Min Act: -0.0001

Data Index: 136761 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.3158. Min Act: -0.0001

Data Index: 73637 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.3138. Min Act: -0.0001

Data Index: 1029879 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.3842. Min Act: -0.0001

Data Index: 447046 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.2431. Min Act: -0.0001

Data Index: 1262414 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.1274. Min Act: -0.0001

Data Index: 1299923 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.3052. Min Act: -0.0001

Data Index: 789109 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.2981. Min Act: -0.0001

Data Index: 651688 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.2815. Min Act: -0.0001

Data Index: 1044712 (C4 (Web Text))

Max Activating Token Index: 652

Text #15

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.2551. Min Act: -0.0001

Data Index: 624550 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.2308. Min Act: -0.0001

Data Index: 1548949 (Python Code)

Max Activating Token Index: 812

Text #17

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.2214. Min Act: -0.0001

Data Index: 675961 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.2166. Min Act: -0.0001

Data Index: 254942 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 1.4931. Min Range: -1.4931

Max Act: 1.2530. Min Act: -0.0001

Data Index: 24565 (C4 (Web Text))

Max Activating Token Index: 727