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

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

Neuron 2345 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9169. Min Range: -1.9169

Max Act: 1.7855. Min Act: -0.0000

Data Index: 315541 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 1.9169. Min Range: -1.9169

Max Act: 1.6555. Min Act: -0.0000

Data Index: 250561 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 1.9169. Min Range: -1.9169

Max Act: 1.9169. Min Act: -0.0000

Data Index: 5323 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 1.9169. Min Range: -1.9169

Max Act: 1.8133. Min Act: -0.0000

Data Index: 1144005 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 1.9169. Min Range: -1.9169

Max Act: 1.7956. Min Act: -0.0000

Data Index: 226970 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 1.9169. Min Range: -1.9169

Max Act: 1.6637. Min Act: -0.0000

Data Index: 1052879 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 1.9169. Min Range: -1.9169

Max Act: 1.6447. Min Act: -0.0000

Data Index: 1302875 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 1.9169. Min Range: -1.9169

Max Act: 1.6615. Min Act: -0.0000

Data Index: 959119 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 1.9169. Min Range: -1.9169

Max Act: 1.6658. Min Act: -0.0000

Data Index: 528958 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 1.9169. Min Range: -1.9169

Max Act: 1.6082. Min Act: -0.0000

Data Index: 1186438 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 1.9169. Min Range: -1.9169

Max Act: 1.6069. Min Act: -0.0000

Data Index: 349089 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 1.9169. Min Range: -1.9169

Max Act: 1.6913. Min Act: -0.0000

Data Index: 327377 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 1.9169. Min Range: -1.9169

Max Act: 1.4876. Min Act: -0.0000

Data Index: 1278267 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 1.9169. Min Range: -1.9169

Max Act: 1.5659. Min Act: -0.0000

Data Index: 1296724 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 1.9169. Min Range: -1.9169

Max Act: 1.4668. Min Act: -0.0000

Data Index: 46285 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 1.9169. Min Range: -1.9169

Max Act: 1.3859. Min Act: -0.0000

Data Index: 1295836 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 1.9169. Min Range: -1.9169

Max Act: 1.5358. Min Act: -0.0000

Data Index: 1291241 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 1.9169. Min Range: -1.9169

Max Act: 1.5189. Min Act: -0.0000

Data Index: 60458 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 1.9169. Min Range: -1.9169

Max Act: 1.6026. Min Act: -0.0000

Data Index: 968677 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 1.9169. Min Range: -1.9169

Max Act: 1.5905. Min Act: -0.0000

Data Index: 627224 (C4 (Web Text))

Max Activating Token Index: 691