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

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

Neuron 2019 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5372. Min Range: -3.5372

Max Act: 3.5372. Min Act: -0.0000

Data Index: 254754 (C4 (Web Text))

Max Activating Token Index: 347

Text #1

Max Range: 3.5372. Min Range: -3.5372

Max Act: 3.4850. Min Act: -0.0000

Data Index: 1278661 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 3.5372. Min Range: -3.5372

Max Act: 3.2279. Min Act: -0.0000

Data Index: 238503 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 3.5372. Min Range: -3.5372

Max Act: 3.0088. Min Act: -0.0000

Data Index: 315109 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 3.5372. Min Range: -3.5372

Max Act: 3.0636. Min Act: -0.0000

Data Index: 24163 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 3.5372. Min Range: -3.5372

Max Act: 2.9158. Min Act: -0.0000

Data Index: 1090361 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 3.5372. Min Range: -3.5372

Max Act: 2.8232. Min Act: -0.0000

Data Index: 347467 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 3.5372. Min Range: -3.5372

Max Act: 2.8993. Min Act: -0.0000

Data Index: 618445 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 3.5372. Min Range: -3.5372

Max Act: 2.7671. Min Act: -0.0000

Data Index: 446639 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 3.5372. Min Range: -3.5372

Max Act: 2.8994. Min Act: -0.0000

Data Index: 732301 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 3.5372. Min Range: -3.5372

Max Act: 2.8826. Min Act: -0.0000

Data Index: 1277564 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 3.5372. Min Range: -3.5372

Max Act: 3.0695. Min Act: -0.0000

Data Index: 1244614 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 3.5372. Min Range: -3.5372

Max Act: 2.4340. Min Act: -0.0000

Data Index: 1059610 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 3.5372. Min Range: -3.5372

Max Act: 2.8046. Min Act: -0.0000

Data Index: 982134 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 3.5372. Min Range: -3.5372

Max Act: 2.7107. Min Act: -0.0000

Data Index: 278693 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 3.5372. Min Range: -3.5372

Max Act: 2.4123. Min Act: -0.0000

Data Index: 278205 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 3.5372. Min Range: -3.5372

Max Act: 2.6606. Min Act: -0.0000

Data Index: 598520 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 3.5372. Min Range: -3.5372

Max Act: 2.6318. Min Act: -0.0000

Data Index: 219844 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 3.5372. Min Range: -3.5372

Max Act: 2.6094. Min Act: -0.0000

Data Index: 283066 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 3.5372. Min Range: -3.5372

Max Act: 2.6147. Min Act: -0.0000

Data Index: 1779 (C4 (Web Text))

Max Activating Token Index: 205