Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1277 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.6990. Min Range: -2.6990

Max Act: 2.6990. Min Act: -0.0000

Data Index: 971571 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 2.6990. Min Range: -2.6990

Max Act: 1.8693. Min Act: -0.0000

Data Index: 1107971 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 2.6990. Min Range: -2.6990

Max Act: 1.7810. Min Act: -0.0000

Data Index: 44998 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 2.6990. Min Range: -2.6990

Max Act: 1.7346. Min Act: -0.0000

Data Index: 377580 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 2.6990. Min Range: -2.6990

Max Act: 1.6310. Min Act: -0.0000

Data Index: 358886 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 2.6990. Min Range: -2.6990

Max Act: 1.4725. Min Act: -0.0000

Data Index: 1152564 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 2.6990. Min Range: -2.6990

Max Act: 1.4185. Min Act: -0.0000

Data Index: 94044 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 2.6990. Min Range: -2.6990

Max Act: 1.3863. Min Act: -0.0000

Data Index: 835660 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 2.6990. Min Range: -2.6990

Max Act: 1.3630. Min Act: -0.0000

Data Index: 305381 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 2.6990. Min Range: -2.6990

Max Act: 1.2913. Min Act: -0.0000

Data Index: 547095 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 2.6990. Min Range: -2.6990

Max Act: 1.2199. Min Act: -0.0000

Data Index: 777600 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 2.6990. Min Range: -2.6990

Max Act: 1.2081. Min Act: -0.0000

Data Index: 6978 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 2.6990. Min Range: -2.6990

Max Act: 1.2801. Min Act: -0.0000

Data Index: 739107 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 2.6990. Min Range: -2.6990

Max Act: 1.2218. Min Act: -0.0000

Data Index: 205547 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 2.6990. Min Range: -2.6990

Max Act: 1.3568. Min Act: -0.0000

Data Index: 1138397 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 2.6990. Min Range: -2.6990

Max Act: 1.2593. Min Act: -0.0000

Data Index: 747390 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 2.6990. Min Range: -2.6990

Max Act: 1.1632. Min Act: -0.0000

Data Index: 716123 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 2.6990. Min Range: -2.6990

Max Act: 1.1280. Min Act: -0.0000

Data Index: 1194265 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 2.6990. Min Range: -2.6990

Max Act: 1.2061. Min Act: -0.0000

Data Index: 1250774 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 2.6990. Min Range: -2.6990

Max Act: 1.2192. Min Act: -0.0000

Data Index: 1000006 (C4 (Web Text))

Max Activating Token Index: 135