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

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

Neuron 3172 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0360. Min Act: -0.0003

Data Index: 882838 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0327. Min Act: -0.0002

Data Index: 625603 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0313. Min Act: -0.0002

Data Index: 1043834 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0313. Min Act: -0.0003

Data Index: 245053 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0312. Min Act: -0.0002

Data Index: 736694 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0302. Min Act: -0.0002

Data Index: 810758 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0303. Min Act: -0.0003

Data Index: 377459 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0307. Min Act: -0.0003

Data Index: 449674 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0307. Min Act: -0.0002

Data Index: 394062 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0305. Min Act: -0.0003

Data Index: 553728 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0301. Min Act: -0.0002

Data Index: 813964 (C4 (Web Text))

Max Activating Token Index: 659

Text #11

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0299. Min Act: -0.0003

Data Index: 258142 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0297. Min Act: -0.0003

Data Index: 642005 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0290. Min Act: -0.0003

Data Index: 146464 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0283. Min Act: -0.0002

Data Index: 537840 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0283. Min Act: -0.0003

Data Index: 778959 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0295. Min Act: -0.0003

Data Index: 435863 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0294. Min Act: -0.0003

Data Index: 1069539 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0279. Min Act: -0.0002

Data Index: 3005 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1106252 (C4 (Web Text))

Max Activating Token Index: 479