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

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

Neuron 298 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.5085. Min Act: -0.0001

Data Index: 471264 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4858. Min Act: -0.0000

Data Index: 623549 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.5085. Min Act: -0.0000

Data Index: 1206891 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4826. Min Act: -0.0001

Data Index: 110599 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4603. Min Act: -0.0001

Data Index: 429371 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4900. Min Act: -0.0001

Data Index: 111687 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4648. Min Act: -0.0001

Data Index: 11641 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4662. Min Act: -0.0001

Data Index: 266250 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4473. Min Act: -0.0001

Data Index: 1189644 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4630. Min Act: -0.0001

Data Index: 678337 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4483. Min Act: -0.0001

Data Index: 328598 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.5078. Min Act: -0.0001

Data Index: 205841 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4427. Min Act: -0.0001

Data Index: 621299 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4050. Min Act: -0.0001

Data Index: 272051 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4417. Min Act: -0.0001

Data Index: 1262596 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4464. Min Act: -0.0000

Data Index: 28727 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4450. Min Act: -0.0001

Data Index: 459163 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4414. Min Act: -0.0001

Data Index: 588527 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4393. Min Act: -0.0000

Data Index: 641360 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 0.5085. Min Range: -0.5085

Max Act: 0.4349. Min Act: -0.0000

Data Index: 890811 (C4 (Web Text))

Max Activating Token Index: 483