Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1010 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.4187. Min Act: -0.1700

Data Index: 410836 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.4344. Min Act: -0.1700

Data Index: 552425 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.3873. Min Act: -0.1700

Data Index: 1275017 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.3716. Min Act: -0.1700

Data Index: 603301 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.3873. Min Act: -0.1700

Data Index: 1152478 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.3716. Min Act: -0.1700

Data Index: 1349826 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.3716. Min Act: -0.1700

Data Index: 439328 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.3716. Min Act: -0.1700

Data Index: 17172 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.3402. Min Act: -0.1700

Data Index: 584829 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.3402. Min Act: -0.1700

Data Index: 1174835 (C4 (Web Text))

Max Activating Token Index: 987

Text #10

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.3559. Min Act: -0.1700

Data Index: 810784 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.3716. Min Act: -0.1700

Data Index: 1319953 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.3402. Min Act: -0.1700

Data Index: 268558 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.3402. Min Act: -0.1700

Data Index: 1220140 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.3245. Min Act: -0.1700

Data Index: 996955 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.3245. Min Act: -0.1700

Data Index: 1156790 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.3559. Min Act: -0.1700

Data Index: 1119830 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.3088. Min Act: -0.1700

Data Index: 380415 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.3245. Min Act: -0.1700

Data Index: 158797 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 3.4344. Min Range: -3.4344

Max Act: 3.3088. Min Act: -0.1700

Data Index: 774437 (C4 (Web Text))

Max Activating Token Index: 497