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

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

Neuron 3374 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.7880. Min Act: -0.0000

Data Index: 1244100 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.7550. Min Act: -0.0000

Data Index: 1259789 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.6727. Min Act: -0.0000

Data Index: 675139 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.6825. Min Act: -0.0000

Data Index: 191591 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.6735. Min Act: -0.0000

Data Index: 838394 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.6296. Min Act: -0.0000

Data Index: 1280314 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.6190. Min Act: -0.0000

Data Index: 1357085 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5512. Min Act: -0.0000

Data Index: 891553 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.6073. Min Act: -0.0000

Data Index: 560369 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.6262. Min Act: -0.0000

Data Index: 643311 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5715. Min Act: -0.0000

Data Index: 1165112 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5686. Min Act: -0.0000

Data Index: 14445 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5529. Min Act: -0.0000

Data Index: 1315148 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5484. Min Act: -0.0000

Data Index: 179437 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5418. Min Act: -0.0000

Data Index: 800117 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5736. Min Act: -0.0000

Data Index: 984443 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5088. Min Act: -0.0000

Data Index: 307349 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5197. Min Act: -0.0000

Data Index: 829565 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5128. Min Act: -0.0000

Data Index: 329679 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 0.7880. Min Range: -0.7880

Max Act: 0.5347. Min Act: -0.0000

Data Index: 414217 (C4 (Web Text))

Max Activating Token Index: 86