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

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

Neuron 2824 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: 0.0438. Min Range: -0.0438

Max Act: 0.0438. Min Act: -0.0001

Data Index: 378707 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0425. Min Act: -0.0001

Data Index: 536869 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0429. Min Act: -0.0001

Data Index: 902268 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0389. Min Act: -0.0001

Data Index: 416905 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0345. Min Act: -0.0001

Data Index: 1278592 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0348. Min Act: -0.0001

Data Index: 1257370 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0335. Min Act: -0.0001

Data Index: 7970 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0336. Min Act: -0.0001

Data Index: 1206179 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0322. Min Act: -0.0001

Data Index: 731388 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0333. Min Act: -0.0001

Data Index: 669656 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0327. Min Act: -0.0001

Data Index: 1308890 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0324. Min Act: -0.0001

Data Index: 575575 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0295. Min Act: -0.0001

Data Index: 1052975 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0301. Min Act: -0.0001

Data Index: 714477 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0298. Min Act: -0.0001

Data Index: 1170410 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0300. Min Act: -0.0001

Data Index: 735529 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0299. Min Act: -0.0001

Data Index: 505889 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0297. Min Act: -0.0001

Data Index: 751002 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0305. Min Act: -0.0001

Data Index: 169370 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0309. Min Act: -0.0001

Data Index: 977163 (C4 (Web Text))

Max Activating Token Index: 813