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

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

Neuron 5856 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: 2.9089. Min Range: -2.9089

Max Act: 2.8067. Min Act: -0.0000

Data Index: 1386009 (Python Code)

Max Activating Token Index: 367

Text #1

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.9089. Min Act: -0.0000

Data Index: 1427069 (Python Code)

Max Activating Token Index: 257

Text #2

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.6607. Min Act: -0.0000

Data Index: 1555537 (Python Code)

Max Activating Token Index: 102

Text #3

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.2521. Min Act: -0.0000

Data Index: 1497575 (Python Code)

Max Activating Token Index: 476

Text #4

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.5043. Min Act: -0.0000

Data Index: 291685 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.1552. Min Act: -0.0000

Data Index: 1485399 (Python Code)

Max Activating Token Index: 941

Text #6

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.0371. Min Act: -0.0000

Data Index: 1535829 (Python Code)

Max Activating Token Index: 133

Text #7

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.2774. Min Act: -0.0000

Data Index: 255181 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.0197. Min Act: -0.0000

Data Index: 1430360 (Python Code)

Max Activating Token Index: 602

Text #9

Max Range: 2.9089. Min Range: -2.9089

Max Act: 1.9953. Min Act: -0.0000

Data Index: 1454906 (Python Code)

Max Activating Token Index: 641

Text #10

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.0600. Min Act: -0.0000

Data Index: 1487231 (Python Code)

Max Activating Token Index: 962

Text #11

Max Range: 2.9089. Min Range: -2.9089

Max Act: 1.9557. Min Act: -0.0000

Data Index: 1407962 (Python Code)

Max Activating Token Index: 715

Text #12

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.0206. Min Act: -0.0000

Data Index: 1523294 (Python Code)

Max Activating Token Index: 369

Text #13

Max Range: 2.9089. Min Range: -2.9089

Max Act: 1.8358. Min Act: -0.0000

Data Index: 623666 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 2.9089. Min Range: -2.9089

Max Act: 1.7246. Min Act: -0.0000

Data Index: 813896 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 2.9089. Min Range: -2.9089

Max Act: 1.7749. Min Act: -0.0000

Data Index: 1566026 (Python Code)

Max Activating Token Index: 36

Text #16

Max Range: 2.9089. Min Range: -2.9089

Max Act: 1.9462. Min Act: -0.0000

Data Index: 1585991 (Python Code)

Max Activating Token Index: 193

Text #17

Max Range: 2.9089. Min Range: -2.9089

Max Act: 1.5816. Min Act: -0.0000

Data Index: 1099464 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 2.9089. Min Range: -2.9089

Max Act: 1.4513. Min Act: -0.0000

Data Index: 282643 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 2.9089. Min Range: -2.9089

Max Act: 1.5803. Min Act: -0.0000

Data Index: 1171233 (C4 (Web Text))

Max Activating Token Index: 696