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

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

Neuron 4710 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4445. Min Range: -2.4445

Max Act: 2.3924. Min Act: -0.0000

Data Index: 1305085 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 2.4445. Min Range: -2.4445

Max Act: 2.4445. Min Act: -0.0000

Data Index: 41404 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 2.4445. Min Range: -2.4445

Max Act: 2.2634. Min Act: -0.0000

Data Index: 401858 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 2.4445. Min Range: -2.4445

Max Act: 2.2403. Min Act: -0.0000

Data Index: 1193209 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 2.4445. Min Range: -2.4445

Max Act: 2.1950. Min Act: -0.0000

Data Index: 719182 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 2.4445. Min Range: -2.4445

Max Act: 2.1464. Min Act: -0.0000

Data Index: 742952 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 2.4445. Min Range: -2.4445

Max Act: 2.0060. Min Act: -0.0000

Data Index: 917280 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 2.4445. Min Range: -2.4445

Max Act: 2.0113. Min Act: -0.0000

Data Index: 375496 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 2.4445. Min Range: -2.4445

Max Act: 2.0828. Min Act: -0.0000

Data Index: 315270 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 2.4445. Min Range: -2.4445

Max Act: 1.9881. Min Act: -0.0000

Data Index: 480745 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 2.4445. Min Range: -2.4445

Max Act: 1.9935. Min Act: -0.0000

Data Index: 167830 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 2.4445. Min Range: -2.4445

Max Act: 1.8773. Min Act: -0.0000

Data Index: 1037717 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 2.4445. Min Range: -2.4445

Max Act: 1.9765. Min Act: -0.0000

Data Index: 107403 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 2.4445. Min Range: -2.4445

Max Act: 1.8240. Min Act: -0.0000

Data Index: 792501 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 2.4445. Min Range: -2.4445

Max Act: 1.9094. Min Act: -0.0000

Data Index: 604355 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 2.4445. Min Range: -2.4445

Max Act: 1.7518. Min Act: -0.0000

Data Index: 856380 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 2.4445. Min Range: -2.4445

Max Act: 1.7648. Min Act: -0.0000

Data Index: 99033 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 2.4445. Min Range: -2.4445

Max Act: 1.9323. Min Act: -0.0000

Data Index: 818249 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 2.4445. Min Range: -2.4445

Max Act: 1.8208. Min Act: -0.0000

Data Index: 994299 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 2.4445. Min Range: -2.4445

Max Act: 1.7685. Min Act: -0.0000

Data Index: 1244912 (C4 (Web Text))

Max Activating Token Index: 395