Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 520 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.4557. Min Act: -0.0000

Data Index: 1008145 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.4622. Min Act: -0.0000

Data Index: 1031425 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.4361. Min Act: -0.0000

Data Index: 307802 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.4472. Min Act: -0.0000

Data Index: 1250821 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.4445. Min Act: -0.0000

Data Index: 510946 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.4295. Min Act: -0.0000

Data Index: 945543 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3889. Min Act: -0.0001

Data Index: 934577 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3870. Min Act: -0.0001

Data Index: 1305349 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3810. Min Act: -0.0000

Data Index: 369290 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3806. Min Act: -0.0000

Data Index: 1102750 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3761. Min Act: -0.0000

Data Index: 1111713 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3530. Min Act: 0.0000

Data Index: 240910 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3628. Min Act: -0.0000

Data Index: 312762 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3628. Min Act: -0.0000

Data Index: 596239 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3759. Min Act: -0.0001

Data Index: 650968 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3541. Min Act: -0.0000

Data Index: 960857 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3372. Min Act: -0.0000

Data Index: 39845 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3472. Min Act: -0.0000

Data Index: 599857 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3100. Min Act: -0.0000

Data Index: 103642 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 0.4622. Min Range: -0.4622

Max Act: 0.3309. Min Act: -0.0000

Data Index: 819297 (C4 (Web Text))

Max Activating Token Index: 448