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

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

Neuron 290 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.7864. Min Act: -0.0002

Data Index: 557344 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.7909. Min Act: -0.0002

Data Index: 1348677 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.9511. Min Act: -0.0002

Data Index: 1239513 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 4.0518. Min Range: -4.0518

Max Act: 4.0518. Min Act: -0.0002

Data Index: 282425 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.6704. Min Act: -0.0002

Data Index: 895029 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.1941. Min Act: -0.0002

Data Index: 1086212 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.5815. Min Act: -0.0002

Data Index: 1179756 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.9284. Min Act: -0.0002

Data Index: 859211 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.1450. Min Act: -0.0002

Data Index: 1131802 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.2460. Min Act: -0.0002

Data Index: 819518 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.0816. Min Act: -0.0002

Data Index: 752295 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.6294. Min Act: -0.0002

Data Index: 1146322 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.2096. Min Act: -0.0002

Data Index: 352097 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.1553. Min Act: -0.0002

Data Index: 832374 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.3113. Min Act: -0.0002

Data Index: 288656 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.0124. Min Act: -0.0002

Data Index: 6243 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.1537. Min Act: -0.0002

Data Index: 1265721 (C4 (Web Text))

Max Activating Token Index: 311

Text #17

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.1656. Min Act: -0.0002

Data Index: 490449 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.4250. Min Act: -0.0002

Data Index: 692360 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 4.0518. Min Range: -4.0518

Max Act: 3.5153. Min Act: -0.0002

Data Index: 754169 (C4 (Web Text))

Max Activating Token Index: 796