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

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

Neuron 1578 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4190. Min Range: -1.4190

Max Act: 1.4190. Min Act: -0.0001

Data Index: 99622 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 1.4190. Min Range: -1.4190

Max Act: 0.9464. Min Act: -0.0001

Data Index: 411062 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 1.4190. Min Range: -1.4190

Max Act: 0.9836. Min Act: -0.0001

Data Index: 1189345 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 1.4190. Min Range: -1.4190

Max Act: 0.9322. Min Act: -0.0001

Data Index: 485561 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 1.4190. Min Range: -1.4190

Max Act: 0.9333. Min Act: -0.0001

Data Index: 973857 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 1.4190. Min Range: -1.4190

Max Act: 0.9257. Min Act: -0.0000

Data Index: 167465 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 1.4190. Min Range: -1.4190

Max Act: 0.9247. Min Act: -0.0001

Data Index: 208159 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 1.4190. Min Range: -1.4190

Max Act: 0.8880. Min Act: -0.0000

Data Index: 534871 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 1.4190. Min Range: -1.4190

Max Act: 0.9015. Min Act: -0.0001

Data Index: 1006660 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 1.4190. Min Range: -1.4190

Max Act: 0.8985. Min Act: -0.0001

Data Index: 393725 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 1.4190. Min Range: -1.4190

Max Act: 0.8261. Min Act: -0.0001

Data Index: 659381 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 1.4190. Min Range: -1.4190

Max Act: 0.8159. Min Act: -0.0000

Data Index: 998644 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 1.4190. Min Range: -1.4190

Max Act: 0.7672. Min Act: -0.0001

Data Index: 1131937 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 1.4190. Min Range: -1.4190

Max Act: 0.8411. Min Act: -0.0001

Data Index: 579458 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 1.4190. Min Range: -1.4190

Max Act: 0.8316. Min Act: -0.0001

Data Index: 31588 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 1.4190. Min Range: -1.4190

Max Act: 0.7761. Min Act: -0.0001

Data Index: 730587 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 1.4190. Min Range: -1.4190

Max Act: 0.7770. Min Act: -0.0000

Data Index: 449293 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 1.4190. Min Range: -1.4190

Max Act: 0.7522. Min Act: -0.0001

Data Index: 805073 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 1.4190. Min Range: -1.4190

Max Act: 0.7713. Min Act: -0.0001

Data Index: 126456 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 1.4190. Min Range: -1.4190

Max Act: 0.8508. Min Act: -0.0001

Data Index: 406427 (C4 (Web Text))

Max Activating Token Index: 685