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

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

Neuron 4831 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1365. Min Range: -3.1365

Max Act: 3.1365. Min Act: -0.0000

Data Index: 516785 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 3.1365. Min Range: -3.1365

Max Act: 2.5500. Min Act: -0.0000

Data Index: 1278171 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 3.1365. Min Range: -3.1365

Max Act: 2.3682. Min Act: -0.0000

Data Index: 265727 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 3.1365. Min Range: -3.1365

Max Act: 2.1220. Min Act: -0.0000

Data Index: 176534 (C4 (Web Text))

Max Activating Token Index: 302

Text #4

Max Range: 3.1365. Min Range: -3.1365

Max Act: 1.6014. Min Act: -0.0000

Data Index: 910717 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 3.1365. Min Range: -3.1365

Max Act: 1.9489. Min Act: -0.0000

Data Index: 290320 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 3.1365. Min Range: -3.1365

Max Act: 1.7366. Min Act: -0.0000

Data Index: 1258200 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 3.1365. Min Range: -3.1365

Max Act: 2.0101. Min Act: -0.0000

Data Index: 617241 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 3.1365. Min Range: -3.1365

Max Act: 2.0015. Min Act: -0.0000

Data Index: 915894 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 3.1365. Min Range: -3.1365

Max Act: 1.8183. Min Act: -0.0000

Data Index: 1260118 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 3.1365. Min Range: -3.1365

Max Act: 1.6933. Min Act: -0.0000

Data Index: 852247 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 3.1365. Min Range: -3.1365

Max Act: 1.7829. Min Act: -0.0000

Data Index: 639218 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 3.1365. Min Range: -3.1365

Max Act: 1.6857. Min Act: -0.0000

Data Index: 466546 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 3.1365. Min Range: -3.1365

Max Act: 1.9421. Min Act: -0.0000

Data Index: 631158 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 3.1365. Min Range: -3.1365

Max Act: 1.7520. Min Act: -0.0000

Data Index: 963302 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 3.1365. Min Range: -3.1365

Max Act: 1.6788. Min Act: -0.0000

Data Index: 75117 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 3.1365. Min Range: -3.1365

Max Act: 1.8433. Min Act: -0.0000

Data Index: 501463 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 3.1365. Min Range: -3.1365

Max Act: 1.9476. Min Act: -0.0000

Data Index: 943343 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 3.1365. Min Range: -3.1365

Max Act: 1.7079. Min Act: -0.0001

Data Index: 685100 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 3.1365. Min Range: -3.1365

Max Act: 1.7923. Min Act: -0.0000

Data Index: 1092186 (C4 (Web Text))

Max Activating Token Index: 300