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

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

Neuron 2069 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4786. Min Range: -1.4786

Max Act: 1.4786. Min Act: -0.0000

Data Index: 454338 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 1.4786. Min Range: -1.4786

Max Act: 1.4302. Min Act: -0.0000

Data Index: 1351222 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 1.4786. Min Range: -1.4786

Max Act: 1.2164. Min Act: -0.0000

Data Index: 1188681 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 1.4786. Min Range: -1.4786

Max Act: 1.1987. Min Act: -0.0000

Data Index: 562394 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 1.4786. Min Range: -1.4786

Max Act: 1.2436. Min Act: -0.0000

Data Index: 1141334 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 1.4786. Min Range: -1.4786

Max Act: 1.1602. Min Act: -0.0000

Data Index: 777126 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 1.4786. Min Range: -1.4786

Max Act: 1.1486. Min Act: -0.0000

Data Index: 1016339 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 1.4786. Min Range: -1.4786

Max Act: 1.0848. Min Act: -0.0000

Data Index: 374473 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 1.4786. Min Range: -1.4786

Max Act: 1.1208. Min Act: -0.0000

Data Index: 1130991 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 1.4786. Min Range: -1.4786

Max Act: 1.1863. Min Act: -0.0000

Data Index: 465244 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 1.4786. Min Range: -1.4786

Max Act: 1.0894. Min Act: -0.0000

Data Index: 543429 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 1.4786. Min Range: -1.4786

Max Act: 1.0452. Min Act: -0.0000

Data Index: 1169239 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 1.4786. Min Range: -1.4786

Max Act: 1.1575. Min Act: -0.0000

Data Index: 437827 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 1.4786. Min Range: -1.4786

Max Act: 1.1233. Min Act: -0.0000

Data Index: 1242470 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 1.4786. Min Range: -1.4786

Max Act: 1.1494. Min Act: -0.0000

Data Index: 781587 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 1.4786. Min Range: -1.4786

Max Act: 1.0587. Min Act: -0.0000

Data Index: 514861 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 1.4786. Min Range: -1.4786

Max Act: 1.1714. Min Act: -0.0000

Data Index: 218949 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 1.4786. Min Range: -1.4786

Max Act: 1.0995. Min Act: -0.0000

Data Index: 942122 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 1.4786. Min Range: -1.4786

Max Act: 1.1318. Min Act: -0.0000

Data Index: 920531 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 1.4786. Min Range: -1.4786

Max Act: 1.1279. Min Act: -0.0000

Data Index: 48305 (C4 (Web Text))

Max Activating Token Index: 979