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

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

Neuron 329 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4074. Min Range: -4.4074

Max Act: 4.4074. Min Act: -0.0000

Data Index: 1340739 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 4.4074. Min Range: -4.4074

Max Act: 4.1452. Min Act: -0.0000

Data Index: 199216 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 4.4074. Min Range: -4.4074

Max Act: 3.9507. Min Act: -0.0000

Data Index: 801064 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 4.4074. Min Range: -4.4074

Max Act: 3.9371. Min Act: -0.0000

Data Index: 1256691 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 4.4074. Min Range: -4.4074

Max Act: 3.8350. Min Act: -0.0000

Data Index: 838094 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 4.4074. Min Range: -4.4074

Max Act: 3.8504. Min Act: -0.0000

Data Index: 16784 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 4.4074. Min Range: -4.4074

Max Act: 3.7982. Min Act: -0.0000

Data Index: 754529 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 4.4074. Min Range: -4.4074

Max Act: 3.6219. Min Act: -0.0000

Data Index: 727122 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 4.4074. Min Range: -4.4074

Max Act: 3.5098. Min Act: -0.0000

Data Index: 1008945 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 4.4074. Min Range: -4.4074

Max Act: 3.6159. Min Act: -0.0000

Data Index: 702650 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 4.4074. Min Range: -4.4074

Max Act: 3.2536. Min Act: -0.0000

Data Index: 1041689 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 4.4074. Min Range: -4.4074

Max Act: 3.3560. Min Act: -0.0000

Data Index: 195782 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 4.4074. Min Range: -4.4074

Max Act: 3.4765. Min Act: -0.0000

Data Index: 543489 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 4.4074. Min Range: -4.4074

Max Act: 3.2862. Min Act: -0.0000

Data Index: 1168665 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 4.4074. Min Range: -4.4074

Max Act: 3.3853. Min Act: -0.0000

Data Index: 1279758 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 4.4074. Min Range: -4.4074

Max Act: 2.8903. Min Act: -0.0000

Data Index: 474861 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 4.4074. Min Range: -4.4074

Max Act: 3.1585. Min Act: -0.0000

Data Index: 4324 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 4.4074. Min Range: -4.4074

Max Act: 3.1330. Min Act: -0.0000

Data Index: 1019833 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 4.4074. Min Range: -4.4074

Max Act: 3.4422. Min Act: -0.0000

Data Index: 486165 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 4.4074. Min Range: -4.4074

Max Act: 2.8174. Min Act: -0.0000

Data Index: 1344712 (C4 (Web Text))

Max Activating Token Index: 753