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

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

Neuron 3299 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3406. Min Range: -1.3406

Max Act: 1.3406. Min Act: -0.0001

Data Index: 118591 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 1.3406. Min Range: -1.3406

Max Act: 1.1921. Min Act: -0.0001

Data Index: 589322 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 1.3406. Min Range: -1.3406

Max Act: 1.2036. Min Act: -0.0001

Data Index: 236688 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 1.3406. Min Range: -1.3406

Max Act: 1.2819. Min Act: -0.0001

Data Index: 543097 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 1.3406. Min Range: -1.3406

Max Act: 1.2100. Min Act: -0.0001

Data Index: 980019 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 1.3406. Min Range: -1.3406

Max Act: 1.2025. Min Act: -0.0001

Data Index: 441463 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 1.3406. Min Range: -1.3406

Max Act: 1.1617. Min Act: -0.0001

Data Index: 1106270 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 1.3406. Min Range: -1.3406

Max Act: 1.1963. Min Act: -0.0001

Data Index: 669059 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 1.3406. Min Range: -1.3406

Max Act: 1.1150. Min Act: -0.0001

Data Index: 754111 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 1.3406. Min Range: -1.3406

Max Act: 1.1326. Min Act: -0.0001

Data Index: 604619 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 1.3406. Min Range: -1.3406

Max Act: 1.0845. Min Act: -0.0001

Data Index: 858843 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 1.3406. Min Range: -1.3406

Max Act: 1.0756. Min Act: -0.0001

Data Index: 1344799 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 1.3406. Min Range: -1.3406

Max Act: 1.0935. Min Act: -0.0001

Data Index: 4926 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 1.3406. Min Range: -1.3406

Max Act: 1.0757. Min Act: -0.0001

Data Index: 100702 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 1.3406. Min Range: -1.3406

Max Act: 1.0541. Min Act: -0.0001

Data Index: 1297345 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 1.3406. Min Range: -1.3406

Max Act: 1.0892. Min Act: -0.0001

Data Index: 134379 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 1.3406. Min Range: -1.3406

Max Act: 1.0672. Min Act: -0.0001

Data Index: 906883 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 1.3406. Min Range: -1.3406

Max Act: 1.0158. Min Act: -0.0001

Data Index: 503439 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 1.3406. Min Range: -1.3406

Max Act: 1.1236. Min Act: -0.0001

Data Index: 734357 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 1.3406. Min Range: -1.3406

Max Act: 0.9853. Min Act: -0.0001

Data Index: 920149 (C4 (Web Text))

Max Activating Token Index: 645