Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 667 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1542. Min Act: -0.0001

Data Index: 12881 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1439. Min Act: -0.0001

Data Index: 748314 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1472. Min Act: -0.0001

Data Index: 413289 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1442. Min Act: -0.0001

Data Index: 983717 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1383. Min Act: -0.0001

Data Index: 86646 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1415. Min Act: -0.0001

Data Index: 914125 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1395. Min Act: -0.0001

Data Index: 1272613 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1379. Min Act: -0.0001

Data Index: 587222 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1316. Min Act: -0.0001

Data Index: 978178 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1250. Min Act: -0.0001

Data Index: 232485 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1256. Min Act: -0.0001

Data Index: 310909 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1218. Min Act: -0.0001

Data Index: 1308556 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1302. Min Act: -0.0001

Data Index: 201299 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.1224. Min Act: -0.0001

Data Index: 1348080 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.0893. Min Act: -0.0001

Data Index: 162156 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.0881. Min Act: -0.0001

Data Index: 702284 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.0812. Min Act: -0.0001

Data Index: 425194 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.0796. Min Act: -0.0001

Data Index: 634513 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.0814. Min Act: -0.0001

Data Index: 615024 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.1542. Min Range: -0.1542

Max Act: 0.0785. Min Act: -0.0001

Data Index: 1354482 (C4 (Web Text))

Max Activating Token Index: 976