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

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

Neuron 4312 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7531. Min Range: -1.7531

Max Act: 1.7531. Min Act: -0.0000

Data Index: 358894 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 1.7531. Min Range: -1.7531

Max Act: 1.6852. Min Act: -0.0000

Data Index: 925494 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 1.7531. Min Range: -1.7531

Max Act: 1.3535. Min Act: -0.0000

Data Index: 668757 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 1.7531. Min Range: -1.7531

Max Act: 1.3307. Min Act: -0.0000

Data Index: 808716 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 1.7531. Min Range: -1.7531

Max Act: 1.0397. Min Act: -0.0000

Data Index: 293010 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 1.7531. Min Range: -1.7531

Max Act: 0.9285. Min Act: 0.0000

Data Index: 494679 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 1.7531. Min Range: -1.7531

Max Act: 0.9168. Min Act: -0.0000

Data Index: 429646 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 1.7531. Min Range: -1.7531

Max Act: 0.8860. Min Act: -0.0000

Data Index: 632676 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 1.7531. Min Range: -1.7531

Max Act: 0.8869. Min Act: -0.0000

Data Index: 616740 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 1.7531. Min Range: -1.7531

Max Act: 0.8241. Min Act: -0.0000

Data Index: 389589 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 1.7531. Min Range: -1.7531

Max Act: 0.8546. Min Act: -0.0000

Data Index: 1236128 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 1.7531. Min Range: -1.7531

Max Act: 0.7964. Min Act: 0.0000

Data Index: 1023479 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 1.7531. Min Range: -1.7531

Max Act: 0.8677. Min Act: -0.0000

Data Index: 902916 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 1.7531. Min Range: -1.7531

Max Act: 0.8373. Min Act: -0.0000

Data Index: 669624 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 1.7531. Min Range: -1.7531

Max Act: 0.7892. Min Act: -0.0000

Data Index: 1076174 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 1.7531. Min Range: -1.7531

Max Act: 0.7855. Min Act: -0.0000

Data Index: 1008333 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 1.7531. Min Range: -1.7531

Max Act: 0.8295. Min Act: -0.0000

Data Index: 521855 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 1.7531. Min Range: -1.7531

Max Act: 0.7820. Min Act: -0.0000

Data Index: 171308 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 1.7531. Min Range: -1.7531

Max Act: 0.7630. Min Act: -0.0000

Data Index: 1068681 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 1.7531. Min Range: -1.7531

Max Act: 0.7087. Min Act: -0.0000

Data Index: 283737 (C4 (Web Text))

Max Activating Token Index: 541