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

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

Neuron 149 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.5224. Min Act: -0.0001

Data Index: 1052110 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.4485. Min Act: -0.0001

Data Index: 1464596 (Python Code)

Max Activating Token Index: 88

Text #2

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.4675. Min Act: -0.0001

Data Index: 1335506 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.4794. Min Act: -0.0001

Data Index: 993323 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.4934. Min Act: -0.0001

Data Index: 428863 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.4764. Min Act: -0.0001

Data Index: 671940 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.4730. Min Act: -0.0001

Data Index: 151731 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.4638. Min Act: -0.0001

Data Index: 282614 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.4368. Min Act: -0.0001

Data Index: 1398634 (Python Code)

Max Activating Token Index: 962

Text #9

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.4704. Min Act: -0.0001

Data Index: 1614399 (Python Code)

Max Activating Token Index: 1013

Text #10

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.4495. Min Act: -0.0001

Data Index: 1223048 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.4350. Min Act: -0.0001

Data Index: 691257 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.4489. Min Act: -0.0001

Data Index: 124935 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.4237. Min Act: -0.0001

Data Index: 397338 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.4354. Min Act: -0.0001

Data Index: 1561740 (Python Code)

Max Activating Token Index: 340

Text #15

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.4064. Min Act: -0.0001

Data Index: 466620 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.4291. Min Act: -0.0001

Data Index: 499438 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.4278. Min Act: -0.0001

Data Index: 1344127 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3956. Min Act: -0.0001

Data Index: 1328333 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.4211. Min Act: -0.0001

Data Index: 1573743 (Python Code)

Max Activating Token Index: 916