Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3342 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.5532. Min Act: -0.0002

Data Index: 473766 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.5111. Min Act: -0.0002

Data Index: 162703 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.5087. Min Act: -0.0002

Data Index: 340964 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.5110. Min Act: -0.0002

Data Index: 697013 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4979. Min Act: -0.0002

Data Index: 415565 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4879. Min Act: -0.0002

Data Index: 463816 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4951. Min Act: -0.0002

Data Index: 657901 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4731. Min Act: -0.0002

Data Index: 183662 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4692. Min Act: -0.0002

Data Index: 188237 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4727. Min Act: -0.0002

Data Index: 1020651 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4647. Min Act: -0.0002

Data Index: 540439 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4593. Min Act: -0.0002

Data Index: 275588 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4523. Min Act: -0.0002

Data Index: 1203279 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4513. Min Act: -0.0002

Data Index: 1327016 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4559. Min Act: -0.0003

Data Index: 1176307 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4482. Min Act: -0.0002

Data Index: 243814 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4554. Min Act: -0.0002

Data Index: 1309393 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4520. Min Act: -0.0002

Data Index: 318677 (C4 (Web Text))

Max Activating Token Index: 940

Text #18

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4593. Min Act: -0.0002

Data Index: 543684 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4502. Min Act: -0.0002

Data Index: 484229 (C4 (Web Text))

Max Activating Token Index: 225