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

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

Neuron 2252 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2107. Min Range: -1.2107

Max Act: 1.2107. Min Act: -0.0000

Data Index: 352499 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 1.2107. Min Range: -1.2107

Max Act: 1.0232. Min Act: -0.0000

Data Index: 1036621 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 1.2107. Min Range: -1.2107

Max Act: 0.9296. Min Act: -0.0000

Data Index: 301863 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 1.2107. Min Range: -1.2107

Max Act: 0.9193. Min Act: -0.0000

Data Index: 1026190 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 1.2107. Min Range: -1.2107

Max Act: 0.8409. Min Act: -0.0000

Data Index: 578485 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 1.2107. Min Range: -1.2107

Max Act: 0.8459. Min Act: -0.0000

Data Index: 366267 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 1.2107. Min Range: -1.2107

Max Act: 0.8420. Min Act: -0.0000

Data Index: 950997 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 1.2107. Min Range: -1.2107

Max Act: 0.8429. Min Act: -0.0000

Data Index: 317381 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 1.2107. Min Range: -1.2107

Max Act: 0.7549. Min Act: -0.0000

Data Index: 561802 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 1.2107. Min Range: -1.2107

Max Act: 0.7464. Min Act: -0.0000

Data Index: 3376 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 1.2107. Min Range: -1.2107

Max Act: 0.7848. Min Act: -0.0000

Data Index: 749504 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 1.2107. Min Range: -1.2107

Max Act: 0.7783. Min Act: -0.0000

Data Index: 170881 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 1.2107. Min Range: -1.2107

Max Act: 0.7715. Min Act: -0.0000

Data Index: 716484 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 1.2107. Min Range: -1.2107

Max Act: 0.7749. Min Act: -0.0000

Data Index: 266816 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 1.2107. Min Range: -1.2107

Max Act: 0.7790. Min Act: -0.0000

Data Index: 112657 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 1.2107. Min Range: -1.2107

Max Act: 0.7837. Min Act: -0.0000

Data Index: 243129 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 1.2107. Min Range: -1.2107

Max Act: 0.7188. Min Act: -0.0000

Data Index: 210211 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 1.2107. Min Range: -1.2107

Max Act: 0.7695. Min Act: -0.0000

Data Index: 1316041 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 1.2107. Min Range: -1.2107

Max Act: 0.7132. Min Act: -0.0000

Data Index: 663189 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 1.2107. Min Range: -1.2107

Max Act: 0.7595. Min Act: -0.0000

Data Index: 233596 (C4 (Web Text))

Max Activating Token Index: 766