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

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

Neuron 749 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: 2.6450. Min Range: -2.6450

Max Act: 2.6450. Min Act: -0.0000

Data Index: 880735 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 2.6450. Min Range: -2.6450

Max Act: 2.3972. Min Act: -0.0000

Data Index: 937581 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 2.6450. Min Range: -2.6450

Max Act: 2.2373. Min Act: -0.0000

Data Index: 96766 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 2.6450. Min Range: -2.6450

Max Act: 2.4521. Min Act: -0.0000

Data Index: 712776 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 2.6450. Min Range: -2.6450

Max Act: 2.4075. Min Act: -0.0000

Data Index: 205988 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 2.6450. Min Range: -2.6450

Max Act: 2.3939. Min Act: -0.0000

Data Index: 1328922 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 2.6450. Min Range: -2.6450

Max Act: 2.4048. Min Act: -0.0000

Data Index: 1175689 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 2.6450. Min Range: -2.6450

Max Act: 2.3542. Min Act: -0.0000

Data Index: 651287 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 2.6450. Min Range: -2.6450

Max Act: 2.2136. Min Act: -0.0000

Data Index: 1318142 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 2.6450. Min Range: -2.6450

Max Act: 2.2108. Min Act: -0.0000

Data Index: 267983 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 2.6450. Min Range: -2.6450

Max Act: 2.1936. Min Act: -0.0000

Data Index: 1221856 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 2.6450. Min Range: -2.6450

Max Act: 2.3077. Min Act: -0.0000

Data Index: 590125 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 2.6450. Min Range: -2.6450

Max Act: 2.2749. Min Act: -0.0000

Data Index: 1140198 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 2.6450. Min Range: -2.6450

Max Act: 2.2485. Min Act: 0.0000

Data Index: 717540 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 2.6450. Min Range: -2.6450

Max Act: 2.2560. Min Act: -0.0000

Data Index: 1269665 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 2.6450. Min Range: -2.6450

Max Act: 2.2475. Min Act: -0.0000

Data Index: 963389 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 2.6450. Min Range: -2.6450

Max Act: 2.0827. Min Act: -0.0000

Data Index: 621012 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 2.6450. Min Range: -2.6450

Max Act: 2.1956. Min Act: -0.0000

Data Index: 793658 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 2.6450. Min Range: -2.6450

Max Act: 2.1834. Min Act: -0.0000

Data Index: 320478 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 2.6450. Min Range: -2.6450

Max Act: 2.1766. Min Act: -0.0000

Data Index: 345367 (C4 (Web Text))

Max Activating Token Index: 155