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

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

Neuron 3202 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0213. Min Range: -3.0213

Max Act: 3.0213. Min Act: -0.0000

Data Index: 862489 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 3.0213. Min Range: -3.0213

Max Act: 3.0105. Min Act: -0.0000

Data Index: 708555 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.9998. Min Act: -0.0000

Data Index: 1268172 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.6279. Min Act: -0.0000

Data Index: 745351 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.6707. Min Act: -0.0000

Data Index: 1211283 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.6664. Min Act: -0.0000

Data Index: 1185068 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.5327. Min Act: -0.0000

Data Index: 976069 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.5456. Min Act: -0.0000

Data Index: 921905 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.5005. Min Act: -0.0000

Data Index: 246363 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 3.0213. Min Range: -3.0213

Max Act: 2.5576. Min Act: -0.0000

Data Index: 1332603 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 3.0213. Min Range: -3.0213

Max Act: 1.9057. Min Act: -0.0000

Data Index: 172887 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 3.0213. Min Range: -3.0213

Max Act: 1.6469. Min Act: -0.0000

Data Index: 1175287 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 3.0213. Min Range: -3.0213

Max Act: 1.5316. Min Act: -0.0000

Data Index: 640858 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 3.0213. Min Range: -3.0213

Max Act: 1.5388. Min Act: -0.0000

Data Index: 1264866 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 3.0213. Min Range: -3.0213

Max Act: 1.4556. Min Act: -0.0000

Data Index: 964822 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 3.0213. Min Range: -3.0213

Max Act: 1.3746. Min Act: -0.0000

Data Index: 353348 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 3.0213. Min Range: -3.0213

Max Act: 1.3654. Min Act: -0.0000

Data Index: 411255 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 3.0213. Min Range: -3.0213

Max Act: 1.3466. Min Act: -0.0000

Data Index: 322065 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 3.0213. Min Range: -3.0213

Max Act: 1.2601. Min Act: -0.0000

Data Index: 143255 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 3.0213. Min Range: -3.0213

Max Act: 1.3143. Min Act: -0.0000

Data Index: 7970 (C4 (Web Text))

Max Activating Token Index: 77