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

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

Neuron 2237 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: 0.3735. Min Range: -0.3735

Max Act: 0.3735. Min Act: -0.0002

Data Index: 1214923 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.3694. Min Act: -0.0001

Data Index: 1036359 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2721. Min Act: -0.0001

Data Index: 687336 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2603. Min Act: -0.0002

Data Index: 1356479 (C4 (Web Text))

Max Activating Token Index: 975

Text #4

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2551. Min Act: -0.0001

Data Index: 338036 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2494. Min Act: -0.0001

Data Index: 796402 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2253. Min Act: -0.0001

Data Index: 306984 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2200. Min Act: -0.0002

Data Index: 1009540 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.1957. Min Act: -0.0002

Data Index: 555070 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2163. Min Act: -0.0001

Data Index: 575096 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2189. Min Act: -0.0002

Data Index: 1353473 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2195. Min Act: -0.0001

Data Index: 407601 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2284. Min Act: -0.0001

Data Index: 550584 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2254. Min Act: -0.0002

Data Index: 924935 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2155. Min Act: -0.0001

Data Index: 1118793 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2133. Min Act: -0.0002

Data Index: 1094277 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2052. Min Act: -0.0002

Data Index: 379176 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2120. Min Act: -0.0002

Data Index: 843833 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2092. Min Act: -0.0001

Data Index: 769141 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 0.3735. Min Range: -0.3735

Max Act: 0.2014. Min Act: -0.0002

Data Index: 821029 (C4 (Web Text))

Max Activating Token Index: 528