Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 383 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6232. Min Range: -0.6232

Max Act: 0.5504. Min Act: -0.0001

Data Index: 195895 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 0.6232. Min Range: -0.6232

Max Act: 0.6232. Min Act: -0.0001

Data Index: 374590 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 0.6232. Min Range: -0.6232

Max Act: 0.5824. Min Act: -0.0001

Data Index: 621816 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 0.6232. Min Range: -0.6232

Max Act: 0.5872. Min Act: -0.0001

Data Index: 251415 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 0.6232. Min Range: -0.6232

Max Act: 0.5828. Min Act: -0.0001

Data Index: 382940 (C4 (Web Text))

Max Activating Token Index: 567

Text #5

Max Range: 0.6232. Min Range: -0.6232

Max Act: 0.5591. Min Act: -0.0001

Data Index: 68986 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.6232. Min Range: -0.6232

Max Act: 0.5427. Min Act: -0.0001

Data Index: 538219 (C4 (Web Text))

Max Activating Token Index: 877

Text #7

Max Range: 0.6232. Min Range: -0.6232

Max Act: 0.5545. Min Act: -0.0001

Data Index: 1266410 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 0.6232. Min Range: -0.6232

Max Act: 0.5493. Min Act: -0.0001

Data Index: 1153997 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 0.6232. Min Range: -0.6232

Max Act: 0.5571. Min Act: -0.0001

Data Index: 1042187 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 0.6232. Min Range: -0.6232

Max Act: 0.5773. Min Act: -0.0001

Data Index: 770003 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 0.6232. Min Range: -0.6232

Max Act: 0.5570. Min Act: -0.0001

Data Index: 463914 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 0.6232. Min Range: -0.6232

Max Act: 0.5866. Min Act: -0.0001

Data Index: 1036914 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 0.6232. Min Range: -0.6232

Max Act: 0.5660. Min Act: -0.0001

Data Index: 232786 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 0.6232. Min Range: -0.6232

Max Act: 0.4849. Min Act: -0.0001

Data Index: 755340 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 0.6232. Min Range: -0.6232

Max Act: 0.5483. Min Act: -0.0001

Data Index: 149078 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 0.6232. Min Range: -0.6232

Max Act: 0.4846. Min Act: -0.0001

Data Index: 658124 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 0.6232. Min Range: -0.6232

Max Act: 0.5204. Min Act: -0.0001

Data Index: 759454 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 0.6232. Min Range: -0.6232

Max Act: 0.5263. Min Act: -0.0001

Data Index: 720770 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 0.6232. Min Range: -0.6232

Max Act: 0.5627. Min Act: -0.0001

Data Index: 838333 (C4 (Web Text))

Max Activating Token Index: 1021