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

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

Neuron 1784 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9012. Min Range: -1.9012

Max Act: 1.9012. Min Act: -0.0000

Data Index: 1197570 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 1.9012. Min Range: -1.9012

Max Act: 1.6557. Min Act: -0.0000

Data Index: 929737 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 1.9012. Min Range: -1.9012

Max Act: 1.5988. Min Act: -0.0000

Data Index: 1342347 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 1.9012. Min Range: -1.9012

Max Act: 1.5000. Min Act: -0.0000

Data Index: 1261299 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 1.9012. Min Range: -1.9012

Max Act: 1.4661. Min Act: -0.0000

Data Index: 836848 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 1.9012. Min Range: -1.9012

Max Act: 1.5299. Min Act: -0.0000

Data Index: 479103 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 1.9012. Min Range: -1.9012

Max Act: 1.4124. Min Act: -0.0000

Data Index: 678982 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 1.9012. Min Range: -1.9012

Max Act: 1.4852. Min Act: -0.0000

Data Index: 1218628 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 1.9012. Min Range: -1.9012

Max Act: 1.2721. Min Act: -0.0000

Data Index: 169108 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 1.9012. Min Range: -1.9012

Max Act: 1.3444. Min Act: -0.0000

Data Index: 599724 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 1.9012. Min Range: -1.9012

Max Act: 1.2770. Min Act: -0.0000

Data Index: 43980 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 1.9012. Min Range: -1.9012

Max Act: 1.3311. Min Act: -0.0000

Data Index: 591573 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 1.9012. Min Range: -1.9012

Max Act: 1.3120. Min Act: -0.0000

Data Index: 239894 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 1.9012. Min Range: -1.9012

Max Act: 1.3148. Min Act: -0.0000

Data Index: 510742 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 1.9012. Min Range: -1.9012

Max Act: 1.3000. Min Act: -0.0000

Data Index: 899624 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 1.9012. Min Range: -1.9012

Max Act: 1.2962. Min Act: -0.0000

Data Index: 764826 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 1.9012. Min Range: -1.9012

Max Act: 1.2897. Min Act: -0.0000

Data Index: 1223183 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 1.9012. Min Range: -1.9012

Max Act: 1.2839. Min Act: -0.0000

Data Index: 1282718 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 1.9012. Min Range: -1.9012

Max Act: 1.2859. Min Act: -0.0000

Data Index: 788748 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 1.9012. Min Range: -1.9012

Max Act: 1.3526. Min Act: -0.0000

Data Index: 919247 (C4 (Web Text))

Max Activating Token Index: 898