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

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

Neuron 5653 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9552. Min Range: -4.9552

Max Act: 4.9552. Min Act: -0.0000

Data Index: 548295 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 4.9552. Min Range: -4.9552

Max Act: 4.5907. Min Act: -0.0000

Data Index: 1217303 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 4.9552. Min Range: -4.9552

Max Act: 4.5591. Min Act: -0.0000

Data Index: 124720 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 4.9552. Min Range: -4.9552

Max Act: 4.4840. Min Act: -0.0000

Data Index: 113897 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 4.9552. Min Range: -4.9552

Max Act: 4.2607. Min Act: -0.0000

Data Index: 779275 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 4.9552. Min Range: -4.9552

Max Act: 3.0515. Min Act: -0.0000

Data Index: 1009841 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 4.9552. Min Range: -4.9552

Max Act: 1.6599. Min Act: -0.0000

Data Index: 580086 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 4.9552. Min Range: -4.9552

Max Act: 1.6325. Min Act: -0.0000

Data Index: 928628 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 4.9552. Min Range: -4.9552

Max Act: 1.3738. Min Act: -0.0000

Data Index: 1281570 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 4.9552. Min Range: -4.9552

Max Act: 1.3179. Min Act: -0.0000

Data Index: 466701 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 4.9552. Min Range: -4.9552

Max Act: 1.2263. Min Act: -0.0000

Data Index: 471566 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 4.9552. Min Range: -4.9552

Max Act: 1.1607. Min Act: -0.0000

Data Index: 108221 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 4.9552. Min Range: -4.9552

Max Act: 1.1138. Min Act: -0.0000

Data Index: 80982 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 4.9552. Min Range: -4.9552

Max Act: 1.1882. Min Act: -0.0000

Data Index: 454863 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 4.9552. Min Range: -4.9552

Max Act: 1.1144. Min Act: -0.0000

Data Index: 1052183 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 4.9552. Min Range: -4.9552

Max Act: 1.0959. Min Act: -0.0000

Data Index: 77630 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 4.9552. Min Range: -4.9552

Max Act: 1.0789. Min Act: 0.0000

Data Index: 1334329 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 4.9552. Min Range: -4.9552

Max Act: 1.0779. Min Act: -0.0000

Data Index: 724198 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 4.9552. Min Range: -4.9552

Max Act: 0.9591. Min Act: -0.0000

Data Index: 988105 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 4.9552. Min Range: -4.9552

Max Act: 1.0257. Min Act: -0.0000

Data Index: 597266 (C4 (Web Text))

Max Activating Token Index: 246