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

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

Neuron 399 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.9647. Min Act: -0.0002

Data Index: 181318 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.8967. Min Act: -0.0002

Data Index: 776390 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.8941. Min Act: -0.0002

Data Index: 581307 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.8657. Min Act: -0.0002

Data Index: 640449 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.8596. Min Act: -0.0002

Data Index: 1337500 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.8597. Min Act: -0.0002

Data Index: 1024063 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.8559. Min Act: -0.0002

Data Index: 652619 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.8586. Min Act: -0.0002

Data Index: 535323 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.8440. Min Act: -0.0002

Data Index: 1022448 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.8508. Min Act: -0.0002

Data Index: 392778 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.8309. Min Act: -0.0002

Data Index: 1015270 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.8258. Min Act: -0.0002

Data Index: 1143593 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.8200. Min Act: -0.0003

Data Index: 1001373 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.8183. Min Act: -0.0002

Data Index: 321323 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.8079. Min Act: -0.0002

Data Index: 260217 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.8198. Min Act: -0.0002

Data Index: 1186713 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.7960. Min Act: -0.0002

Data Index: 284123 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.8127. Min Act: -0.0002

Data Index: 908253 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.7978. Min Act: -0.0002

Data Index: 444911 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 0.9647. Min Range: -0.9647

Max Act: 0.7971. Min Act: -0.0002

Data Index: 1253758 (C4 (Web Text))

Max Activating Token Index: 815