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

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

Neuron 2117 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: 6.5854. Min Range: -6.5854

Max Act: 6.5854. Min Act: -0.0000

Data Index: 116007 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 6.5854. Min Range: -6.5854

Max Act: 6.3963. Min Act: -0.0000

Data Index: 1252184 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 6.5854. Min Range: -6.5854

Max Act: 6.3836. Min Act: -0.0000

Data Index: 557087 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 6.5854. Min Range: -6.5854

Max Act: 5.6977. Min Act: -0.0000

Data Index: 1317087 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 6.5854. Min Range: -6.5854

Max Act: 5.1599. Min Act: -0.0000

Data Index: 740805 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 6.5854. Min Range: -6.5854

Max Act: 5.4040. Min Act: -0.0000

Data Index: 706315 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 6.5854. Min Range: -6.5854

Max Act: 5.7545. Min Act: -0.0000

Data Index: 716321 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 6.5854. Min Range: -6.5854

Max Act: 5.7169. Min Act: -0.0000

Data Index: 371285 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 6.5854. Min Range: -6.5854

Max Act: 5.6988. Min Act: -0.0000

Data Index: 136034 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 6.5854. Min Range: -6.5854

Max Act: 5.5127. Min Act: -0.0000

Data Index: 140579 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 6.5854. Min Range: -6.5854

Max Act: 5.5282. Min Act: -0.0000

Data Index: 858610 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 6.5854. Min Range: -6.5854

Max Act: 5.8740. Min Act: -0.0000

Data Index: 600351 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 6.5854. Min Range: -6.5854

Max Act: 5.6206. Min Act: -0.0000

Data Index: 408763 (C4 (Web Text))

Max Activating Token Index: 705

Text #13

Max Range: 6.5854. Min Range: -6.5854

Max Act: 5.2542. Min Act: -0.0000

Data Index: 10612 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 6.5854. Min Range: -6.5854

Max Act: 5.5783. Min Act: -0.0000

Data Index: 1030220 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 6.5854. Min Range: -6.5854

Max Act: 5.7000. Min Act: -0.0000

Data Index: 719060 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 6.5854. Min Range: -6.5854

Max Act: 4.9944. Min Act: -0.0000

Data Index: 292367 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 6.5854. Min Range: -6.5854

Max Act: 5.5170. Min Act: -0.0000

Data Index: 472456 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 6.5854. Min Range: -6.5854

Max Act: 5.2543. Min Act: -0.0000

Data Index: 706574 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 6.5854. Min Range: -6.5854

Max Act: 5.4202. Min Act: -0.0000

Data Index: 1131526 (C4 (Web Text))

Max Activating Token Index: 567