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

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

Neuron 91 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.4278. Min Act: -0.0000

Data Index: 344499 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.4003. Min Act: -0.0000

Data Index: 255995 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.4331. Min Act: -0.0000

Data Index: 555574 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.4013. Min Act: -0.0000

Data Index: 21587 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.3727. Min Act: -0.0000

Data Index: 758645 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.4064. Min Act: -0.0000

Data Index: 128961 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.3954. Min Act: -0.0000

Data Index: 524732 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.3752. Min Act: -0.0000

Data Index: 60365 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.3734. Min Act: -0.0000

Data Index: 282402 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.3642. Min Act: -0.0000

Data Index: 1426849 (Python Code)

Max Activating Token Index: 475

Text #10

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.3498. Min Act: -0.0000

Data Index: 1341804 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.3735. Min Act: -0.0000

Data Index: 296621 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.3729. Min Act: -0.0000

Data Index: 358654 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.3507. Min Act: -0.0000

Data Index: 1289912 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.3527. Min Act: -0.0000

Data Index: 1262479 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.3565. Min Act: -0.0000

Data Index: 1064532 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.3440. Min Act: -0.0000

Data Index: 608240 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.3342. Min Act: -0.0000

Data Index: 900635 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.3418. Min Act: 0.0000

Data Index: 702244 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 0.4331. Min Range: -0.4331

Max Act: 0.3432. Min Act: -0.0000

Data Index: 662422 (C4 (Web Text))

Max Activating Token Index: 647