Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1090 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.6034. Min Range: -6.6034

Max Act: 6.6034. Min Act: -0.0000

Data Index: 286963 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 6.6034. Min Range: -6.6034

Max Act: 6.0179. Min Act: -0.0000

Data Index: 79467 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 6.6034. Min Range: -6.6034

Max Act: 6.0777. Min Act: -0.0000

Data Index: 940467 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 6.6034. Min Range: -6.6034

Max Act: 5.9130. Min Act: -0.0000

Data Index: 1076202 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 6.6034. Min Range: -6.6034

Max Act: 5.7645. Min Act: -0.0000

Data Index: 635158 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 6.6034. Min Range: -6.6034

Max Act: 5.7203. Min Act: -0.0000

Data Index: 1041715 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 6.6034. Min Range: -6.6034

Max Act: 5.7470. Min Act: -0.0000

Data Index: 1322592 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 6.6034. Min Range: -6.6034

Max Act: 5.2518. Min Act: -0.0000

Data Index: 579509 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 6.6034. Min Range: -6.6034

Max Act: 5.5346. Min Act: -0.0000

Data Index: 1084509 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 6.6034. Min Range: -6.6034

Max Act: 5.2916. Min Act: -0.0000

Data Index: 102593 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 6.6034. Min Range: -6.6034

Max Act: 5.1371. Min Act: -0.0000

Data Index: 302013 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 6.6034. Min Range: -6.6034

Max Act: 5.4682. Min Act: -0.0000

Data Index: 838181 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 6.6034. Min Range: -6.6034

Max Act: 5.2623. Min Act: -0.0000

Data Index: 536103 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 6.6034. Min Range: -6.6034

Max Act: 5.1584. Min Act: -0.0000

Data Index: 1121867 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 6.6034. Min Range: -6.6034

Max Act: 5.5321. Min Act: -0.0000

Data Index: 1074155 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 6.6034. Min Range: -6.6034

Max Act: 5.0465. Min Act: -0.0000

Data Index: 669807 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 6.6034. Min Range: -6.6034

Max Act: 5.0427. Min Act: -0.0000

Data Index: 607690 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 6.6034. Min Range: -6.6034

Max Act: 5.0464. Min Act: -0.0000

Data Index: 1252766 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 6.6034. Min Range: -6.6034

Max Act: 4.8466. Min Act: -0.0000

Data Index: 1171140 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 6.6034. Min Range: -6.6034

Max Act: 5.0242. Min Act: -0.0000

Data Index: 713841 (C4 (Web Text))

Max Activating Token Index: 756