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

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

Neuron 5412 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2407. Min Act: -0.0001

Data Index: 654035 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2499. Min Act: -0.0001

Data Index: 772206 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2631. Min Act: -0.0001

Data Index: 448349 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2546. Min Act: -0.0001

Data Index: 907960 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2329. Min Act: -0.0001

Data Index: 1325151 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2347. Min Act: -0.0001

Data Index: 833052 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2380. Min Act: -0.0002

Data Index: 848781 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2230. Min Act: -0.0001

Data Index: 560100 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1992. Min Act: -0.0001

Data Index: 938812 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2206. Min Act: -0.0001

Data Index: 1011989 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2052. Min Act: -0.0001

Data Index: 1156972 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1991. Min Act: -0.0001

Data Index: 237316 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2250. Min Act: -0.0001

Data Index: 780639 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2032. Min Act: -0.0001

Data Index: 435117 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1909. Min Act: -0.0001

Data Index: 1151725 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1986. Min Act: -0.0001

Data Index: 1032685 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1960. Min Act: -0.0001

Data Index: 235792 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2040. Min Act: -0.0001

Data Index: 497410 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.1909. Min Act: -0.0001

Data Index: 700718 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 0.2631. Min Range: -0.2631

Max Act: 0.2055. Min Act: -0.0001

Data Index: 256601 (C4 (Web Text))

Max Activating Token Index: 878