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

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

Neuron 4754 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0330. Min Act: -0.0002

Data Index: 404256 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0252. Min Act: -0.0002

Data Index: 957078 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0192. Min Act: -0.0002

Data Index: 341426 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0182. Min Act: -0.0002

Data Index: 1193984 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0181. Min Act: -0.0002

Data Index: 140379 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0171. Min Act: -0.0002

Data Index: 91411 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0161. Min Act: -0.0002

Data Index: 1028378 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0170. Min Act: -0.0002

Data Index: 148473 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0192. Min Act: -0.0002

Data Index: 405986 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0179. Min Act: -0.0002

Data Index: 454191 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0145. Min Act: -0.0002

Data Index: 188999 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0169. Min Act: -0.0002

Data Index: 498057 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0157. Min Act: -0.0002

Data Index: 531306 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0166. Min Act: -0.0002

Data Index: 585852 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0135. Min Act: -0.0002

Data Index: 991998 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0164. Min Act: -0.0002

Data Index: 74278 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0145. Min Act: -0.0002

Data Index: 1287654 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0161. Min Act: -0.0002

Data Index: 1343354 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0124. Min Act: -0.0002

Data Index: 569458 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 0.0330. Min Range: -0.0330

Max Act: 0.0152. Min Act: -0.0002

Data Index: 352729 (C4 (Web Text))

Max Activating Token Index: 916