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

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

Neuron 1401 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.8108. Min Act: -0.0000

Data Index: 1595968 (Python Code)

Max Activating Token Index: 536

Text #1

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.7365. Min Act: 0.0001

Data Index: 1554603 (Python Code)

Max Activating Token Index: 247

Text #2

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.7031. Min Act: -0.0000

Data Index: 1317682 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.7424. Min Act: 0.0000

Data Index: 1572433 (Python Code)

Max Activating Token Index: 871

Text #4

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.7218. Min Act: -0.0000

Data Index: 1458123 (Python Code)

Max Activating Token Index: 297

Text #5

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6886. Min Act: -0.0000

Data Index: 1576620 (Python Code)

Max Activating Token Index: 90

Text #6

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6538. Min Act: -0.0000

Data Index: 1428639 (Python Code)

Max Activating Token Index: 722

Text #7

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.7243. Min Act: -0.0000

Data Index: 1437545 (Python Code)

Max Activating Token Index: 371

Text #8

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6577. Min Act: 0.0001

Data Index: 1623078 (Python Code)

Max Activating Token Index: 117

Text #9

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6748. Min Act: -0.0000

Data Index: 1406587 (Python Code)

Max Activating Token Index: 819

Text #10

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6606. Min Act: 0.0000

Data Index: 1391990 (Python Code)

Max Activating Token Index: 256

Text #11

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6538. Min Act: -0.0000

Data Index: 1343900 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6481. Min Act: 0.0000

Data Index: 1372152 (Python Code)

Max Activating Token Index: 672

Text #13

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6401. Min Act: -0.0000

Data Index: 93594 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6237. Min Act: -0.0000

Data Index: 1417194 (Python Code)

Max Activating Token Index: 145

Text #15

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6204. Min Act: 0.0000

Data Index: 1387115 (Python Code)

Max Activating Token Index: 70

Text #16

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6195. Min Act: 0.0000

Data Index: 1508104 (Python Code)

Max Activating Token Index: 58

Text #17

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6155. Min Act: -0.0000

Data Index: 1601833 (Python Code)

Max Activating Token Index: 497

Text #18

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6226. Min Act: -0.0000

Data Index: 1366203 (Python Code)

Max Activating Token Index: 875

Text #19

Max Range: 0.8108. Min Range: -0.8108

Max Act: 0.6095. Min Act: -0.0000

Data Index: 1637519 (Python Code)

Max Activating Token Index: 418