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

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

Neuron 3541 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: 2.4709. Min Range: -2.4709

Max Act: 2.4709. Min Act: -0.0000

Data Index: 513120 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 2.4709. Min Range: -2.4709

Max Act: 2.2301. Min Act: -0.0000

Data Index: 880420 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 2.4709. Min Range: -2.4709

Max Act: 1.8306. Min Act: -0.0000

Data Index: 276216 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 2.4709. Min Range: -2.4709

Max Act: 1.8312. Min Act: -0.0000

Data Index: 218161 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 2.4709. Min Range: -2.4709

Max Act: 1.5149. Min Act: -0.0000

Data Index: 1353840 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 2.4709. Min Range: -2.4709

Max Act: 1.6270. Min Act: -0.0000

Data Index: 445778 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 2.4709. Min Range: -2.4709

Max Act: 1.7728. Min Act: -0.0000

Data Index: 1144315 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 2.4709. Min Range: -2.4709

Max Act: 1.7371. Min Act: -0.0000

Data Index: 691966 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 2.4709. Min Range: -2.4709

Max Act: 1.7605. Min Act: -0.0000

Data Index: 1179927 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 2.4709. Min Range: -2.4709

Max Act: 1.7672. Min Act: -0.0000

Data Index: 811631 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 2.4709. Min Range: -2.4709

Max Act: 1.6601. Min Act: -0.0000

Data Index: 1197022 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 2.4709. Min Range: -2.4709

Max Act: 1.6558. Min Act: -0.0000

Data Index: 1213982 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 2.4709. Min Range: -2.4709

Max Act: 1.6438. Min Act: -0.0000

Data Index: 38861 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 2.4709. Min Range: -2.4709

Max Act: 1.5071. Min Act: -0.0000

Data Index: 148941 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 2.4709. Min Range: -2.4709

Max Act: 1.6280. Min Act: -0.0000

Data Index: 1093429 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 2.4709. Min Range: -2.4709

Max Act: 1.6216. Min Act: -0.0000

Data Index: 651632 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 2.4709. Min Range: -2.4709

Max Act: 1.6948. Min Act: -0.0000

Data Index: 646288 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 2.4709. Min Range: -2.4709

Max Act: 1.5195. Min Act: -0.0000

Data Index: 121055 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 2.4709. Min Range: -2.4709

Max Act: 1.6585. Min Act: -0.0000

Data Index: 1321708 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 2.4709. Min Range: -2.4709

Max Act: 1.6334. Min Act: -0.0000

Data Index: 205609 (C4 (Web Text))

Max Activating Token Index: 864