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

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

Neuron 2330 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0636. Min Act: -0.0003

Data Index: 340024 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0582. Min Act: -0.0003

Data Index: 1173913 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0474. Min Act: -0.0003

Data Index: 868263 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0465. Min Act: -0.0003

Data Index: 1320014 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0457. Min Act: -0.0003

Data Index: 982132 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0459. Min Act: -0.0003

Data Index: 1124880 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0444. Min Act: -0.0003

Data Index: 869111 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0440. Min Act: -0.0003

Data Index: 1271353 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0491. Min Act: -0.0004

Data Index: 1146017 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0431. Min Act: -0.0003

Data Index: 1117299 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0457. Min Act: -0.0004

Data Index: 47317 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0429. Min Act: -0.0003

Data Index: 18676 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0421. Min Act: -0.0003

Data Index: 935700 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0439. Min Act: -0.0003

Data Index: 83578 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0438. Min Act: -0.0003

Data Index: 1182585 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0437. Min Act: -0.0003

Data Index: 346889 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0425. Min Act: -0.0003

Data Index: 48737 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0436. Min Act: -0.0003

Data Index: 437625 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0422. Min Act: -0.0003

Data Index: 1274245 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0419. Min Act: -0.0003

Data Index: 1181153 (C4 (Web Text))

Max Activating Token Index: 803