Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5237 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.2431. Min Act: -0.0000

Data Index: 26035 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.2348. Min Act: -0.0000

Data Index: 844585 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.2227. Min Act: -0.0000

Data Index: 1094114 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.2006. Min Act: -0.0000

Data Index: 46618 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.2126. Min Act: -0.0000

Data Index: 278617 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1951. Min Act: -0.0000

Data Index: 551972 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1998. Min Act: -0.0000

Data Index: 662672 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1712. Min Act: -0.0000

Data Index: 807353 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1699. Min Act: -0.0000

Data Index: 1228040 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1618. Min Act: -0.0000

Data Index: 536084 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1589. Min Act: -0.0000

Data Index: 1496485 (Python Code)

Max Activating Token Index: 61

Text #11

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1660. Min Act: -0.0000

Data Index: 1451416 (Python Code)

Max Activating Token Index: 114

Text #12

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1599. Min Act: -0.0000

Data Index: 1561613 (Python Code)

Max Activating Token Index: 58

Text #13

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1543. Min Act: -0.0000

Data Index: 1337797 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1466. Min Act: -0.0000

Data Index: 1450435 (Python Code)

Max Activating Token Index: 166

Text #15

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1497. Min Act: -0.0000

Data Index: 197723 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1537. Min Act: -0.0000

Data Index: 1380560 (Python Code)

Max Activating Token Index: 102

Text #17

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1609. Min Act: -0.0000

Data Index: 1107658 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1434. Min Act: -0.0000

Data Index: 1306254 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1503. Min Act: -0.0000

Data Index: 85269 (C4 (Web Text))

Max Activating Token Index: 327