Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1818 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0359. Min Act: -0.0004

Data Index: 325105 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0288. Min Act: -0.0004

Data Index: 925587 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0278. Min Act: -0.0004

Data Index: 1299439 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0280. Min Act: -0.0004

Data Index: 399606 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0262. Min Act: -0.0004

Data Index: 1044191 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0261. Min Act: -0.0004

Data Index: 1074296 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0250. Min Act: -0.0004

Data Index: 847512 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0255. Min Act: -0.0004

Data Index: 407139 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0254. Min Act: -0.0004

Data Index: 647816 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0259. Min Act: -0.0004

Data Index: 876465 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0246. Min Act: -0.0004

Data Index: 778330 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0243. Min Act: -0.0004

Data Index: 1097075 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0247. Min Act: -0.0004

Data Index: 868026 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0246. Min Act: -0.0004

Data Index: 317191 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0240. Min Act: -0.0004

Data Index: 494904 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0238. Min Act: -0.0004

Data Index: 515639 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0240. Min Act: -0.0004

Data Index: 803834 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0240. Min Act: -0.0004

Data Index: 604534 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0229. Min Act: -0.0004

Data Index: 258434 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0237. Min Act: -0.0004

Data Index: 1070846 (C4 (Web Text))

Max Activating Token Index: 508