Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2319 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.8246. Min Act: -0.0000

Data Index: 6205 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.8666. Min Act: -0.0000

Data Index: 64906 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.7331. Min Act: -0.0000

Data Index: 1188418 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.6857. Min Act: -0.0000

Data Index: 679945 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.6592. Min Act: -0.0000

Data Index: 1310306 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.7068. Min Act: -0.0000

Data Index: 158317 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.6465. Min Act: -0.0000

Data Index: 437759 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.6082. Min Act: -0.0000

Data Index: 1178983 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.5931. Min Act: -0.0000

Data Index: 256471 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.5722. Min Act: -0.0000

Data Index: 316492 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.6303. Min Act: -0.0000

Data Index: 983049 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.6272. Min Act: -0.0000

Data Index: 542776 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.5839. Min Act: -0.0000

Data Index: 878797 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.5995. Min Act: -0.0000

Data Index: 908620 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.6320. Min Act: -0.0000

Data Index: 1167348 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.4901. Min Act: -0.0000

Data Index: 1401437 (Python Code)

Max Activating Token Index: 910

Text #16

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.5979. Min Act: -0.0000

Data Index: 204975 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.5661. Min Act: -0.0000

Data Index: 374353 (C4 (Web Text))

Max Activating Token Index: 434

Text #18

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.6015. Min Act: -0.0000

Data Index: 320300 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 0.8666. Min Range: -0.8666

Max Act: 0.5618. Min Act: -0.0000

Data Index: 96118 (C4 (Web Text))

Max Activating Token Index: 806