Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1080 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.2435. Min Range: -3.2435

Max Act: 3.1184. Min Act: 0.0000

Data Index: 1445214 (Python Code)

Max Activating Token Index: 820

Text #1

Max Range: 3.2435. Min Range: -3.2435

Max Act: 3.1268. Min Act: -0.0000

Data Index: 1515972 (Python Code)

Max Activating Token Index: 833

Text #2

Max Range: 3.2435. Min Range: -3.2435

Max Act: 3.1138. Min Act: 0.0001

Data Index: 1500481 (Python Code)

Max Activating Token Index: 279

Text #3

Max Range: 3.2435. Min Range: -3.2435

Max Act: 3.2435. Min Act: 0.0001

Data Index: 1418911 (Python Code)

Max Activating Token Index: 96

Text #4

Max Range: 3.2435. Min Range: -3.2435

Max Act: 2.9510. Min Act: -0.0000

Data Index: 1433595 (Python Code)

Max Activating Token Index: 759

Text #5

Max Range: 3.2435. Min Range: -3.2435

Max Act: 2.8143. Min Act: -0.0000

Data Index: 1513563 (Python Code)

Max Activating Token Index: 1008

Text #6

Max Range: 3.2435. Min Range: -3.2435

Max Act: 2.7940. Min Act: -0.0000

Data Index: 1390444 (Python Code)

Max Activating Token Index: 316

Text #7

Max Range: 3.2435. Min Range: -3.2435

Max Act: 2.7379. Min Act: 0.0001

Data Index: 1611552 (Python Code)

Max Activating Token Index: 210

Text #8

Max Range: 3.2435. Min Range: -3.2435

Max Act: 2.7193. Min Act: -0.0000

Data Index: 1467161 (Python Code)

Max Activating Token Index: 65

Text #9

Max Range: 3.2435. Min Range: -3.2435

Max Act: 2.5312. Min Act: -0.0000

Data Index: 1483613 (Python Code)

Max Activating Token Index: 951

Text #10

Max Range: 3.2435. Min Range: -3.2435

Max Act: 2.6514. Min Act: -0.0000

Data Index: 1433413 (Python Code)

Max Activating Token Index: 259

Text #11

Max Range: 3.2435. Min Range: -3.2435

Max Act: 2.3691. Min Act: -0.0000

Data Index: 1512566 (Python Code)

Max Activating Token Index: 202

Text #12

Max Range: 3.2435. Min Range: -3.2435

Max Act: 2.4913. Min Act: 0.0001

Data Index: 1396557 (Python Code)

Max Activating Token Index: 15

Text #13

Max Range: 3.2435. Min Range: -3.2435

Max Act: 2.4575. Min Act: -0.0000

Data Index: 1422558 (Python Code)

Max Activating Token Index: 498

Text #14

Max Range: 3.2435. Min Range: -3.2435

Max Act: 2.4633. Min Act: -0.0000

Data Index: 1607196 (Python Code)

Max Activating Token Index: 333

Text #15

Max Range: 3.2435. Min Range: -3.2435

Max Act: 2.3209. Min Act: 0.0000

Data Index: 1431800 (Python Code)

Max Activating Token Index: 474

Text #16

Max Range: 3.2435. Min Range: -3.2435

Max Act: 2.2462. Min Act: 0.0001

Data Index: 1618689 (Python Code)

Max Activating Token Index: 148

Text #17

Max Range: 3.2435. Min Range: -3.2435

Max Act: 2.2224. Min Act: 0.0000

Data Index: 1390675 (Python Code)

Max Activating Token Index: 10

Text #18

Max Range: 3.2435. Min Range: -3.2435

Max Act: 2.1935. Min Act: -0.0000

Data Index: 1478140 (Python Code)

Max Activating Token Index: 20

Text #19

Max Range: 3.2435. Min Range: -3.2435

Max Act: 1.9971. Min Act: -0.0000

Data Index: 1497029 (Python Code)

Max Activating Token Index: 632