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

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

Neuron 3253 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0754. Min Range: -3.0754

Max Act: 3.0754. Min Act: -0.0000

Data Index: 28097 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 3.0754. Min Range: -3.0754

Max Act: 2.8475. Min Act: -0.0000

Data Index: 961111 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 3.0754. Min Range: -3.0754

Max Act: 2.8402. Min Act: -0.0000

Data Index: 740384 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 3.0754. Min Range: -3.0754

Max Act: 2.9030. Min Act: -0.0000

Data Index: 374738 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 3.0754. Min Range: -3.0754

Max Act: 2.8177. Min Act: -0.0001

Data Index: 125871 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 3.0754. Min Range: -3.0754

Max Act: 2.4138. Min Act: -0.0001

Data Index: 840873 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 3.0754. Min Range: -3.0754

Max Act: 2.2947. Min Act: -0.0001

Data Index: 642342 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 3.0754. Min Range: -3.0754

Max Act: 2.4077. Min Act: -0.0001

Data Index: 270675 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 3.0754. Min Range: -3.0754

Max Act: 2.3793. Min Act: -0.0000

Data Index: 861752 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 3.0754. Min Range: -3.0754

Max Act: 2.2415. Min Act: -0.0000

Data Index: 38507 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 3.0754. Min Range: -3.0754

Max Act: 2.3334. Min Act: -0.0000

Data Index: 487533 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 3.0754. Min Range: -3.0754

Max Act: 2.2394. Min Act: -0.0000

Data Index: 409947 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 3.0754. Min Range: -3.0754

Max Act: 1.9979. Min Act: -0.0000

Data Index: 55977 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 3.0754. Min Range: -3.0754

Max Act: 1.9574. Min Act: -0.0001

Data Index: 339231 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 3.0754. Min Range: -3.0754

Max Act: 2.0383. Min Act: -0.0001

Data Index: 899207 (C4 (Web Text))

Max Activating Token Index: 686

Text #15

Max Range: 3.0754. Min Range: -3.0754

Max Act: 1.9192. Min Act: -0.0001

Data Index: 319125 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 3.0754. Min Range: -3.0754

Max Act: 2.0234. Min Act: -0.0001

Data Index: 983703 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 3.0754. Min Range: -3.0754

Max Act: 2.0158. Min Act: -0.0000

Data Index: 432201 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 3.0754. Min Range: -3.0754

Max Act: 1.6925. Min Act: -0.0000

Data Index: 433555 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 3.0754. Min Range: -3.0754

Max Act: 1.9649. Min Act: -0.0001

Data Index: 49531 (C4 (Web Text))

Max Activating Token Index: 21