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

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

Neuron 1147 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7761. Min Range: -2.7761

Max Act: 2.7131. Min Act: -0.0000

Data Index: 1470659 (Python Code)

Max Activating Token Index: 803

Text #1

Max Range: 2.7761. Min Range: -2.7761

Max Act: 2.4417. Min Act: -0.0000

Data Index: 1623330 (Python Code)

Max Activating Token Index: 858

Text #2

Max Range: 2.7761. Min Range: -2.7761

Max Act: 2.4104. Min Act: -0.0001

Data Index: 1403407 (Python Code)

Max Activating Token Index: 845

Text #3

Max Range: 2.7761. Min Range: -2.7761

Max Act: 2.6544. Min Act: -0.0001

Data Index: 1555596 (Python Code)

Max Activating Token Index: 698

Text #4

Max Range: 2.7761. Min Range: -2.7761

Max Act: 2.7761. Min Act: -0.0001

Data Index: 1494577 (Python Code)

Max Activating Token Index: 864

Text #5

Max Range: 2.7761. Min Range: -2.7761

Max Act: 2.4174. Min Act: -0.0001

Data Index: 1525950 (Python Code)

Max Activating Token Index: 793

Text #6

Max Range: 2.7761. Min Range: -2.7761

Max Act: 2.2124. Min Act: -0.0000

Data Index: 1454732 (Python Code)

Max Activating Token Index: 751

Text #7

Max Range: 2.7761. Min Range: -2.7761

Max Act: 2.4200. Min Act: -0.0000

Data Index: 1379055 (Python Code)

Max Activating Token Index: 890

Text #8

Max Range: 2.7761. Min Range: -2.7761

Max Act: 2.4454. Min Act: -0.0000

Data Index: 1368387 (Python Code)

Max Activating Token Index: 847

Text #9

Max Range: 2.7761. Min Range: -2.7761

Max Act: 2.3864. Min Act: -0.0000

Data Index: 1628210 (Python Code)

Max Activating Token Index: 900

Text #10

Max Range: 2.7761. Min Range: -2.7761

Max Act: 2.5004. Min Act: -0.0000

Data Index: 1610159 (Python Code)

Max Activating Token Index: 973

Text #11

Max Range: 2.7761. Min Range: -2.7761

Max Act: 2.3858. Min Act: -0.0000

Data Index: 1567915 (Python Code)

Max Activating Token Index: 267

Text #12

Max Range: 2.7761. Min Range: -2.7761

Max Act: 2.3874. Min Act: -0.0000

Data Index: 1636257 (Python Code)

Max Activating Token Index: 714

Text #13

Max Range: 2.7761. Min Range: -2.7761

Max Act: 2.3473. Min Act: -0.0000

Data Index: 1387932 (Python Code)

Max Activating Token Index: 111

Text #14

Max Range: 2.7761. Min Range: -2.7761

Max Act: 2.3776. Min Act: -0.0000

Data Index: 1627597 (Python Code)

Max Activating Token Index: 890

Text #15

Max Range: 2.7761. Min Range: -2.7761

Max Act: 2.5016. Min Act: -0.0000

Data Index: 1570247 (Python Code)

Max Activating Token Index: 778

Text #16

Max Range: 2.7761. Min Range: -2.7761

Max Act: 2.6136. Min Act: -0.0000

Data Index: 1644117 (Python Code)

Max Activating Token Index: 58

Text #17

Max Range: 2.7761. Min Range: -2.7761

Max Act: 2.3295. Min Act: -0.0000

Data Index: 1558713 (Python Code)

Max Activating Token Index: 846

Text #18

Max Range: 2.7761. Min Range: -2.7761

Max Act: 2.4751. Min Act: -0.0001

Data Index: 1459972 (Python Code)

Max Activating Token Index: 1012

Text #19

Max Range: 2.7761. Min Range: -2.7761

Max Act: 2.3324. Min Act: -0.0000

Data Index: 1368689 (Python Code)

Max Activating Token Index: 969