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

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

Neuron 4687 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: 1.9986. Min Range: -1.9986

Max Act: 1.9986. Min Act: -0.0000

Data Index: 569960 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 1.9986. Min Range: -1.9986

Max Act: 1.8672. Min Act: -0.0000

Data Index: 166811 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 1.9986. Min Range: -1.9986

Max Act: 1.7897. Min Act: -0.0000

Data Index: 37168 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 1.9986. Min Range: -1.9986

Max Act: 1.5587. Min Act: -0.0000

Data Index: 295846 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 1.9986. Min Range: -1.9986

Max Act: 1.3963. Min Act: -0.0000

Data Index: 522228 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 1.9986. Min Range: -1.9986

Max Act: 1.3604. Min Act: -0.0000

Data Index: 409522 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 1.9986. Min Range: -1.9986

Max Act: 1.2517. Min Act: -0.0000

Data Index: 115408 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 1.9986. Min Range: -1.9986

Max Act: 1.0899. Min Act: -0.0000

Data Index: 1168862 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 1.9986. Min Range: -1.9986

Max Act: 1.1938. Min Act: -0.0000

Data Index: 1163217 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 1.9986. Min Range: -1.9986

Max Act: 1.1778. Min Act: -0.0000

Data Index: 541573 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 1.9986. Min Range: -1.9986

Max Act: 1.1277. Min Act: -0.0000

Data Index: 1192259 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 1.9986. Min Range: -1.9986

Max Act: 0.9454. Min Act: -0.0000

Data Index: 300883 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 1.9986. Min Range: -1.9986

Max Act: 0.9711. Min Act: -0.0000

Data Index: 1104362 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 1.9986. Min Range: -1.9986

Max Act: 0.9573. Min Act: -0.0000

Data Index: 987519 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 1.9986. Min Range: -1.9986

Max Act: 0.9414. Min Act: -0.0000

Data Index: 509950 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 1.9986. Min Range: -1.9986

Max Act: 0.9807. Min Act: -0.0000

Data Index: 922880 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 1.9986. Min Range: -1.9986

Max Act: 0.9168. Min Act: -0.0000

Data Index: 1135198 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 1.9986. Min Range: -1.9986

Max Act: 0.9785. Min Act: -0.0000

Data Index: 932609 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 1.9986. Min Range: -1.9986

Max Act: 0.9741. Min Act: -0.0000

Data Index: 1127189 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 1.9986. Min Range: -1.9986

Max Act: 0.9336. Min Act: -0.0000

Data Index: 482767 (C4 (Web Text))

Max Activating Token Index: 14