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

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

Neuron 914 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2517. Min Range: -2.2517

Max Act: 2.2517. Min Act: -0.0000

Data Index: 1548316 (Python Code)

Max Activating Token Index: 662

Text #1

Max Range: 2.2517. Min Range: -2.2517

Max Act: 1.8907. Min Act: -0.0000

Data Index: 62834 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 2.2517. Min Range: -2.2517

Max Act: 1.6664. Min Act: -0.0000

Data Index: 1617131 (Python Code)

Max Activating Token Index: 58

Text #3

Max Range: 2.2517. Min Range: -2.2517

Max Act: 2.0527. Min Act: -0.0000

Data Index: 1433250 (Python Code)

Max Activating Token Index: 276

Text #4

Max Range: 2.2517. Min Range: -2.2517

Max Act: 1.5425. Min Act: -0.0000

Data Index: 720263 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 2.2517. Min Range: -2.2517

Max Act: 1.7160. Min Act: -0.0000

Data Index: 1360789 (Python Code)

Max Activating Token Index: 212

Text #6

Max Range: 2.2517. Min Range: -2.2517

Max Act: 1.8050. Min Act: -0.0000

Data Index: 1546542 (Python Code)

Max Activating Token Index: 312

Text #7

Max Range: 2.2517. Min Range: -2.2517

Max Act: 1.5956. Min Act: -0.0000

Data Index: 1489652 (Python Code)

Max Activating Token Index: 242

Text #8

Max Range: 2.2517. Min Range: -2.2517

Max Act: 1.5780. Min Act: -0.0000

Data Index: 1646358 (Python Code)

Max Activating Token Index: 963

Text #9

Max Range: 2.2517. Min Range: -2.2517

Max Act: 1.6280. Min Act: -0.0000

Data Index: 737808 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 2.2517. Min Range: -2.2517

Max Act: 1.7253. Min Act: -0.0000

Data Index: 1525944 (Python Code)

Max Activating Token Index: 31

Text #11

Max Range: 2.2517. Min Range: -2.2517

Max Act: 1.6194. Min Act: -0.0000

Data Index: 500988 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 2.2517. Min Range: -2.2517

Max Act: 1.5742. Min Act: -0.0000

Data Index: 1548621 (Python Code)

Max Activating Token Index: 1018

Text #13

Max Range: 2.2517. Min Range: -2.2517

Max Act: 1.4890. Min Act: -0.0000

Data Index: 1086681 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 2.2517. Min Range: -2.2517

Max Act: 1.4687. Min Act: -0.0000

Data Index: 1431335 (Python Code)

Max Activating Token Index: 207

Text #15

Max Range: 2.2517. Min Range: -2.2517

Max Act: 1.3923. Min Act: -0.0000

Data Index: 669371 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 2.2517. Min Range: -2.2517

Max Act: 1.5244. Min Act: -0.0000

Data Index: 1597999 (Python Code)

Max Activating Token Index: 668

Text #17

Max Range: 2.2517. Min Range: -2.2517

Max Act: 1.6295. Min Act: -0.0000

Data Index: 278620 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 2.2517. Min Range: -2.2517

Max Act: 1.4282. Min Act: -0.0000

Data Index: 1459027 (Python Code)

Max Activating Token Index: 685

Text #19

Max Range: 2.2517. Min Range: -2.2517

Max Act: 1.6139. Min Act: -0.0000

Data Index: 1418871 (Python Code)

Max Activating Token Index: 100