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

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

Neuron 4420 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.4284. Min Act: -0.0001

Data Index: 981914 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.2225. Min Act: -0.0001

Data Index: 130366 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.3204. Min Act: -0.0001

Data Index: 730598 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.2816. Min Act: -0.0001

Data Index: 747927 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.2852. Min Act: -0.0001

Data Index: 200448 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.2480. Min Act: -0.0001

Data Index: 34189 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.2289. Min Act: -0.0001

Data Index: 1221553 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.1369. Min Act: -0.0001

Data Index: 864946 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.1912. Min Act: -0.0001

Data Index: 295103 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.1100. Min Act: -0.0001

Data Index: 949396 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.1335. Min Act: -0.0001

Data Index: 923496 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.1144. Min Act: -0.0001

Data Index: 722737 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.0515. Min Act: -0.0001

Data Index: 989230 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.1243. Min Act: -0.0001

Data Index: 220644 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.0786. Min Act: -0.0001

Data Index: 382063 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.0480. Min Act: -0.0001

Data Index: 278217 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.0223. Min Act: -0.0001

Data Index: 998910 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.0086. Min Act: -0.0001

Data Index: 81278 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 1.4284. Min Range: -1.4284

Max Act: 1.0651. Min Act: -0.0001

Data Index: 1035003 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 1.4284. Min Range: -1.4284

Max Act: 0.9362. Min Act: -0.0001

Data Index: 1338042 (C4 (Web Text))

Max Activating Token Index: 63