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

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

Neuron 3317 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3172. Min Range: -2.3172

Max Act: 2.3172. Min Act: -0.0000

Data Index: 1284997 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 2.3172. Min Range: -2.3172

Max Act: 1.8218. Min Act: -0.0000

Data Index: 745167 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 2.3172. Min Range: -2.3172

Max Act: 1.7994. Min Act: -0.0000

Data Index: 1026587 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 2.3172. Min Range: -2.3172

Max Act: 1.6558. Min Act: -0.0000

Data Index: 392498 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 2.3172. Min Range: -2.3172

Max Act: 1.7492. Min Act: -0.0000

Data Index: 215550 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 2.3172. Min Range: -2.3172

Max Act: 1.8368. Min Act: -0.0000

Data Index: 138698 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 2.3172. Min Range: -2.3172

Max Act: 1.7509. Min Act: -0.0000

Data Index: 951095 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 2.3172. Min Range: -2.3172

Max Act: 1.6816. Min Act: -0.0000

Data Index: 334999 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 2.3172. Min Range: -2.3172

Max Act: 1.5455. Min Act: -0.0000

Data Index: 220506 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 2.3172. Min Range: -2.3172

Max Act: 1.7582. Min Act: -0.0000

Data Index: 542080 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 2.3172. Min Range: -2.3172

Max Act: 1.8065. Min Act: -0.0000

Data Index: 1102526 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 2.3172. Min Range: -2.3172

Max Act: 1.5964. Min Act: -0.0000

Data Index: 98669 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 2.3172. Min Range: -2.3172

Max Act: 1.6703. Min Act: -0.0000

Data Index: 219087 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 2.3172. Min Range: -2.3172

Max Act: 1.6250. Min Act: -0.0000

Data Index: 88651 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 2.3172. Min Range: -2.3172

Max Act: 1.6177. Min Act: -0.0000

Data Index: 481577 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 2.3172. Min Range: -2.3172

Max Act: 1.6610. Min Act: -0.0000

Data Index: 1314546 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 2.3172. Min Range: -2.3172

Max Act: 1.6566. Min Act: -0.0000

Data Index: 762614 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 2.3172. Min Range: -2.3172

Max Act: 1.6534. Min Act: -0.0000

Data Index: 680214 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 2.3172. Min Range: -2.3172

Max Act: 1.5577. Min Act: -0.0000

Data Index: 1137121 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 2.3172. Min Range: -2.3172

Max Act: 1.6952. Min Act: -0.0000

Data Index: 1100985 (C4 (Web Text))

Max Activating Token Index: 706