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

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

Neuron 4052 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5222. Min Range: -1.5222

Max Act: 1.5222. Min Act: -0.0000

Data Index: 1143284 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 1.5222. Min Range: -1.5222

Max Act: 1.2297. Min Act: -0.0000

Data Index: 510664 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 1.5222. Min Range: -1.5222

Max Act: 0.9877. Min Act: -0.0000

Data Index: 1175271 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 1.5222. Min Range: -1.5222

Max Act: 0.9545. Min Act: -0.0000

Data Index: 332764 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 1.5222. Min Range: -1.5222

Max Act: 0.9211. Min Act: -0.0000

Data Index: 1243734 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 1.5222. Min Range: -1.5222

Max Act: 0.9091. Min Act: -0.0000

Data Index: 1277865 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 1.5222. Min Range: -1.5222

Max Act: 0.8426. Min Act: -0.0000

Data Index: 358235 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 1.5222. Min Range: -1.5222

Max Act: 0.9593. Min Act: -0.0000

Data Index: 741318 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 1.5222. Min Range: -1.5222

Max Act: 0.9274. Min Act: -0.0000

Data Index: 1206645 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 1.5222. Min Range: -1.5222

Max Act: 0.8373. Min Act: -0.0000

Data Index: 576154 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 1.5222. Min Range: -1.5222

Max Act: 0.9445. Min Act: -0.0000

Data Index: 865624 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 1.5222. Min Range: -1.5222

Max Act: 0.9428. Min Act: -0.0000

Data Index: 1209241 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 1.5222. Min Range: -1.5222

Max Act: 0.9345. Min Act: -0.0000

Data Index: 336030 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 1.5222. Min Range: -1.5222

Max Act: 0.9159. Min Act: -0.0000

Data Index: 866318 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 1.5222. Min Range: -1.5222

Max Act: 0.7695. Min Act: -0.0000

Data Index: 198169 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 1.5222. Min Range: -1.5222

Max Act: 0.8557. Min Act: -0.0000

Data Index: 956045 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 1.5222. Min Range: -1.5222

Max Act: 0.8566. Min Act: -0.0000

Data Index: 686595 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 1.5222. Min Range: -1.5222

Max Act: 0.8524. Min Act: -0.0000

Data Index: 781455 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 1.5222. Min Range: -1.5222

Max Act: 0.9327. Min Act: -0.0000

Data Index: 1197875 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 1.5222. Min Range: -1.5222

Max Act: 0.8667. Min Act: -0.0000

Data Index: 254352 (C4 (Web Text))

Max Activating Token Index: 250