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

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

Neuron 3276 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.6310. Min Act: -0.0001

Data Index: 758792 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.6077. Min Act: -0.0001

Data Index: 352999 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.6159. Min Act: -0.0001

Data Index: 366663 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.6034. Min Act: -0.0001

Data Index: 877194 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.6050. Min Act: -0.0001

Data Index: 720979 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5810. Min Act: -0.0001

Data Index: 29087 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5575. Min Act: -0.0001

Data Index: 1139632 (C4 (Web Text))

Max Activating Token Index: 989

Text #7

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5523. Min Act: -0.0001

Data Index: 1037442 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5658. Min Act: -0.0001

Data Index: 935498 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5661. Min Act: -0.0001

Data Index: 669498 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5619. Min Act: -0.0001

Data Index: 43058 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5805. Min Act: -0.0001

Data Index: 1025394 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5414. Min Act: -0.0001

Data Index: 632827 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5614. Min Act: -0.0001

Data Index: 281503 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5667. Min Act: -0.0001

Data Index: 778819 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5438. Min Act: -0.0001

Data Index: 134831 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5174. Min Act: -0.0001

Data Index: 1239924 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5000. Min Act: -0.0001

Data Index: 936219 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.5339. Min Act: -0.0001

Data Index: 747691 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 0.6310. Min Range: -0.6310

Max Act: 0.4628. Min Act: -0.0001

Data Index: 668768 (C4 (Web Text))

Max Activating Token Index: 641