Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3196 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.9861. Min Act: -0.0001

Data Index: 155775 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.9226. Min Act: -0.0001

Data Index: 128571 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.8291. Min Act: -0.0001

Data Index: 1352197 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.7910. Min Act: -0.0001

Data Index: 505176 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.7697. Min Act: -0.0001

Data Index: 554323 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.8108. Min Act: -0.0001

Data Index: 1284899 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.8546. Min Act: -0.0001

Data Index: 55075 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.8086. Min Act: -0.0001

Data Index: 97201 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.7786. Min Act: -0.0001

Data Index: 379975 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.7973. Min Act: -0.0001

Data Index: 803171 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.7648. Min Act: -0.0001

Data Index: 588055 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.8007. Min Act: -0.0001

Data Index: 264392 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.7828. Min Act: -0.0001

Data Index: 149516 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.7716. Min Act: -0.0001

Data Index: 1037049 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.7826. Min Act: -0.0001

Data Index: 345884 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.7179. Min Act: -0.0001

Data Index: 1173674 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.7411. Min Act: -0.0001

Data Index: 114525 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.7326. Min Act: -0.0001

Data Index: 451163 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.7306. Min Act: -0.0001

Data Index: 1356748 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.7779. Min Act: -0.0001

Data Index: 846497 (C4 (Web Text))

Max Activating Token Index: 602