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

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

Neuron 789 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.3237. Min Act: -0.0000

Data Index: 1195866 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.2703. Min Act: -0.0000

Data Index: 1116175 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.2576. Min Act: -0.0000

Data Index: 531264 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.2572. Min Act: -0.0000

Data Index: 787364 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.2367. Min Act: -0.0000

Data Index: 684184 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.2448. Min Act: -0.0000

Data Index: 291862 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.2260. Min Act: -0.0000

Data Index: 832354 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.2337. Min Act: -0.0000

Data Index: 211150 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.2314. Min Act: -0.0000

Data Index: 67608 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.2530. Min Act: 0.0000

Data Index: 948486 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.2362. Min Act: -0.0000

Data Index: 274022 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.2355. Min Act: -0.0000

Data Index: 1102569 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.2182. Min Act: -0.0000

Data Index: 895208 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.2117. Min Act: -0.0000

Data Index: 1202572 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.2338. Min Act: -0.0000

Data Index: 1161242 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.2166. Min Act: -0.0000

Data Index: 1077608 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.2338. Min Act: -0.0000

Data Index: 1173437 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.2304. Min Act: -0.0000

Data Index: 694416 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.2154. Min Act: -0.0000

Data Index: 272435 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 0.3237. Min Range: -0.3237

Max Act: 0.2081. Min Act: -0.0000

Data Index: 1011007 (C4 (Web Text))

Max Activating Token Index: 524