Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 811 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.2743. Min Act: -0.1700

Data Index: 762227 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.2585. Min Act: -0.1700

Data Index: 717426 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.2428. Min Act: -0.1700

Data Index: 316098 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.2428. Min Act: -0.1700

Data Index: 861332 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.2271. Min Act: -0.1700

Data Index: 1187947 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.1956. Min Act: -0.1700

Data Index: 245424 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.1956. Min Act: -0.1700

Data Index: 56022 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.1956. Min Act: -0.1700

Data Index: 397749 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.1642. Min Act: -0.1700

Data Index: 592552 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.1642. Min Act: -0.1700

Data Index: 1232138 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.1799. Min Act: -0.1700

Data Index: 571698 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.1484. Min Act: -0.1700

Data Index: 1123815 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.1484. Min Act: -0.1700

Data Index: 1187519 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.1642. Min Act: -0.1700

Data Index: 640094 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.1327. Min Act: -0.1700

Data Index: 622206 (C4 (Web Text))

Max Activating Token Index: 310

Text #15

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.1169. Min Act: -0.1700

Data Index: 560318 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.1327. Min Act: -0.1700

Data Index: 885943 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.1327. Min Act: -0.1700

Data Index: 765124 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.1169. Min Act: -0.1700

Data Index: 912979 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.1169. Min Act: -0.1700

Data Index: 114927 (C4 (Web Text))

Max Activating Token Index: 883