Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2191 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.4206. Min Range: -2.4206

Max Act: 2.4206. Min Act: -0.0000

Data Index: 628992 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 2.4206. Min Range: -2.4206

Max Act: 2.1988. Min Act: -0.0000

Data Index: 23136 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 2.4206. Min Range: -2.4206

Max Act: 2.0313. Min Act: -0.0001

Data Index: 1177579 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 2.4206. Min Range: -2.4206

Max Act: 2.0084. Min Act: -0.0001

Data Index: 196210 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 2.4206. Min Range: -2.4206

Max Act: 2.1015. Min Act: -0.0001

Data Index: 1276400 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 2.4206. Min Range: -2.4206

Max Act: 1.8598. Min Act: -0.0001

Data Index: 885204 (C4 (Web Text))

Max Activating Token Index: 422

Text #6

Max Range: 2.4206. Min Range: -2.4206

Max Act: 1.7367. Min Act: -0.0000

Data Index: 1007963 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 2.4206. Min Range: -2.4206

Max Act: 1.8337. Min Act: -0.0000

Data Index: 764006 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 2.4206. Min Range: -2.4206

Max Act: 2.0366. Min Act: -0.0001

Data Index: 861381 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 2.4206. Min Range: -2.4206

Max Act: 1.7745. Min Act: -0.0000

Data Index: 602181 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 2.4206. Min Range: -2.4206

Max Act: 1.7420. Min Act: -0.0001

Data Index: 1308330 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 2.4206. Min Range: -2.4206

Max Act: 1.7318. Min Act: -0.0001

Data Index: 212115 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 2.4206. Min Range: -2.4206

Max Act: 1.8224. Min Act: -0.0000

Data Index: 985774 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 2.4206. Min Range: -2.4206

Max Act: 1.8137. Min Act: -0.0000

Data Index: 319192 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 2.4206. Min Range: -2.4206

Max Act: 1.6816. Min Act: -0.0001

Data Index: 1191688 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 2.4206. Min Range: -2.4206

Max Act: 1.6427. Min Act: -0.0000

Data Index: 500268 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 2.4206. Min Range: -2.4206

Max Act: 1.5734. Min Act: -0.0001

Data Index: 1328988 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 2.4206. Min Range: -2.4206

Max Act: 1.6162. Min Act: -0.0001

Data Index: 506821 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 2.4206. Min Range: -2.4206

Max Act: 1.6796. Min Act: -0.0001

Data Index: 1221351 (C4 (Web Text))

Max Activating Token Index: 617

Text #19

Max Range: 2.4206. Min Range: -2.4206

Max Act: 1.7616. Min Act: -0.0001

Data Index: 552300 (C4 (Web Text))

Max Activating Token Index: 129