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

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

Neuron 4457 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.3002. Min Act: -0.0001

Data Index: 1218772 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.3158. Min Act: -0.0000

Data Index: 78669 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2937. Min Act: -0.0000

Data Index: 958835 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.3046. Min Act: -0.0000

Data Index: 870208 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2646. Min Act: -0.0000

Data Index: 1344414 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2375. Min Act: -0.0000

Data Index: 136065 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2176. Min Act: -0.0000

Data Index: 165832 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2285. Min Act: -0.0000

Data Index: 488466 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2509. Min Act: -0.0000

Data Index: 734921 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2017. Min Act: -0.0000

Data Index: 924535 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2293. Min Act: -0.0001

Data Index: 164632 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2407. Min Act: -0.0001

Data Index: 1561367 (Python Code)

Max Activating Token Index: 282

Text #12

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2185. Min Act: -0.0000

Data Index: 237106 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2218. Min Act: -0.0001

Data Index: 292474 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2150. Min Act: -0.0000

Data Index: 1011691 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2204. Min Act: -0.0000

Data Index: 1118893 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2124. Min Act: -0.0001

Data Index: 1397345 (Python Code)

Max Activating Token Index: 58

Text #17

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2600. Min Act: -0.0000

Data Index: 570727 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.2193. Min Act: -0.0001

Data Index: 292515 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 0.3158. Min Range: -0.3158

Max Act: 0.1568. Min Act: -0.0000

Data Index: 143138 (C4 (Web Text))

Max Activating Token Index: 772