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

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

Neuron 2874 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.9421. Min Act: -0.0001

Data Index: 1346239 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.9429. Min Act: -0.0001

Data Index: 1184749 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.9985. Min Act: -0.0001

Data Index: 178332 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.7943. Min Act: -0.0001

Data Index: 1133139 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.8645. Min Act: -0.0001

Data Index: 831987 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.8160. Min Act: -0.0001

Data Index: 793770 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.7474. Min Act: -0.0001

Data Index: 19288 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.7915. Min Act: -0.0001

Data Index: 339663 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.8324. Min Act: -0.0001

Data Index: 1337182 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.8032. Min Act: -0.0001

Data Index: 216274 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.6875. Min Act: -0.0001

Data Index: 492108 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.7454. Min Act: -0.0001

Data Index: 250653 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.5965. Min Act: -0.0001

Data Index: 175949 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.6948. Min Act: -0.0001

Data Index: 1328503 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.7219. Min Act: -0.0001

Data Index: 421729 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.5245. Min Act: -0.0001

Data Index: 770307 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.7483. Min Act: -0.0001

Data Index: 720823 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.6437. Min Act: -0.0001

Data Index: 1064872 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.6298. Min Act: -0.0001

Data Index: 26215 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 1.9985. Min Range: -1.9985

Max Act: 1.6151. Min Act: -0.0001

Data Index: 836248 (C4 (Web Text))

Max Activating Token Index: 133