Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 911 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3975. Min Act: -0.0006

Data Index: 1313794 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3537. Min Act: -0.0006

Data Index: 72938 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3775. Min Act: -0.0006

Data Index: 1278145 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3755. Min Act: -0.0006

Data Index: 912432 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3709. Min Act: -0.0006

Data Index: 267547 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3669. Min Act: -0.0006

Data Index: 508450 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3784. Min Act: -0.0006

Data Index: 910358 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3612. Min Act: -0.0006

Data Index: 1181637 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3698. Min Act: -0.0006

Data Index: 191355 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3575. Min Act: -0.0006

Data Index: 1227892 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3562. Min Act: -0.0006

Data Index: 954850 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3546. Min Act: -0.0006

Data Index: 453757 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3517. Min Act: -0.0006

Data Index: 81348 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3364. Min Act: -0.0006

Data Index: 693658 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3343. Min Act: -0.0005

Data Index: 199392 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3316. Min Act: -0.0006

Data Index: 705450 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3305. Min Act: -0.0006

Data Index: 588068 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3415. Min Act: -0.0006

Data Index: 787743 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3751. Min Act: -0.0006

Data Index: 95115 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3254. Min Act: -0.0006

Data Index: 565545 (C4 (Web Text))

Max Activating Token Index: 818