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

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

Neuron 4785 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2239. Min Range: -4.2239

Max Act: 4.1692. Min Act: -0.0000

Data Index: 1224625 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 4.2239. Min Range: -4.2239

Max Act: 4.2239. Min Act: -0.0000

Data Index: 758068 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 4.2239. Min Range: -4.2239

Max Act: 3.8130. Min Act: 0.0000

Data Index: 1140370 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 4.2239. Min Range: -4.2239

Max Act: 3.6386. Min Act: 0.0000

Data Index: 662697 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 4.2239. Min Range: -4.2239

Max Act: 3.5455. Min Act: -0.0000

Data Index: 781223 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 4.2239. Min Range: -4.2239

Max Act: 3.3046. Min Act: 0.0001

Data Index: 39782 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 4.2239. Min Range: -4.2239

Max Act: 3.1605. Min Act: -0.0000

Data Index: 1183942 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 4.2239. Min Range: -4.2239

Max Act: 3.1124. Min Act: -0.0000

Data Index: 700919 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 4.2239. Min Range: -4.2239

Max Act: 3.3541. Min Act: -0.0000

Data Index: 437413 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 4.2239. Min Range: -4.2239

Max Act: 3.1833. Min Act: 0.0000

Data Index: 509610 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 4.2239. Min Range: -4.2239

Max Act: 3.1327. Min Act: 0.0001

Data Index: 833306 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 4.2239. Min Range: -4.2239

Max Act: 2.9263. Min Act: 0.0001

Data Index: 633987 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 4.2239. Min Range: -4.2239

Max Act: 3.0763. Min Act: -0.0000

Data Index: 245438 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 4.2239. Min Range: -4.2239

Max Act: 2.7725. Min Act: -0.0000

Data Index: 959987 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 4.2239. Min Range: -4.2239

Max Act: 3.0170. Min Act: -0.0000

Data Index: 193708 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 4.2239. Min Range: -4.2239

Max Act: 3.0522. Min Act: 0.0002

Data Index: 837391 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 4.2239. Min Range: -4.2239

Max Act: 2.8633. Min Act: 0.0001

Data Index: 1217546 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 4.2239. Min Range: -4.2239

Max Act: 3.2451. Min Act: 0.0001

Data Index: 1035329 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 4.2239. Min Range: -4.2239

Max Act: 3.1130. Min Act: 0.0000

Data Index: 1149687 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 4.2239. Min Range: -4.2239

Max Act: 2.7745. Min Act: 0.0001

Data Index: 895293 (C4 (Web Text))

Max Activating Token Index: 649