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

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

Neuron 2062 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.5394. Min Act: -0.0001

Data Index: 876199 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4423. Min Act: -0.0002

Data Index: 1181562 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4551. Min Act: -0.0002

Data Index: 482561 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4323. Min Act: -0.0001

Data Index: 524807 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4438. Min Act: -0.0001

Data Index: 899107 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4241. Min Act: -0.0002

Data Index: 1214090 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4196. Min Act: -0.0001

Data Index: 258312 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4437. Min Act: -0.0001

Data Index: 1058672 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4150. Min Act: -0.0002

Data Index: 764304 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4175. Min Act: -0.0001

Data Index: 846856 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4122. Min Act: -0.0002

Data Index: 372229 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4248. Min Act: -0.0002

Data Index: 316356 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.3943. Min Act: -0.0002

Data Index: 531907 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.3946. Min Act: -0.0001

Data Index: 49294 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.3983. Min Act: -0.0002

Data Index: 458466 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4004. Min Act: -0.0001

Data Index: 954356 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.3863. Min Act: -0.0002

Data Index: 822146 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.3773. Min Act: -0.0002

Data Index: 127338 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.3777. Min Act: -0.0002

Data Index: 1110314 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.3805. Min Act: -0.0002

Data Index: 826514 (C4 (Web Text))

Max Activating Token Index: 925