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

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

Neuron 3719 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.3161. Min Act: 0.0000

Data Index: 36557 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2575. Min Act: -0.0000

Data Index: 469298 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2584. Min Act: -0.0000

Data Index: 972832 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2352. Min Act: -0.0000

Data Index: 188003 (C4 (Web Text))

Max Activating Token Index: 626

Text #4

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2561. Min Act: -0.0000

Data Index: 464306 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2297. Min Act: -0.0000

Data Index: 801191 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2347. Min Act: -0.0000

Data Index: 186475 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2330. Min Act: -0.0000

Data Index: 149959 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2693. Min Act: 0.0001

Data Index: 1022225 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2323. Min Act: -0.0000

Data Index: 1262502 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2330. Min Act: 0.0001

Data Index: 571957 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2455. Min Act: -0.0000

Data Index: 43484 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2316. Min Act: -0.0000

Data Index: 318187 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2214. Min Act: 0.0001

Data Index: 977263 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2139. Min Act: -0.0000

Data Index: 1261102 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2172. Min Act: -0.0000

Data Index: 952057 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2100. Min Act: -0.0000

Data Index: 123890 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2102. Min Act: -0.0000

Data Index: 1244532 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2216. Min Act: 0.0000

Data Index: 662457 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2063. Min Act: -0.0000

Data Index: 731952 (C4 (Web Text))

Max Activating Token Index: 378