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

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

Neuron 818 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2295. Min Range: -5.2295

Max Act: 5.2295. Min Act: -0.1700

Data Index: 1060258 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 5.2295. Min Range: -5.2295

Max Act: 5.1982. Min Act: -0.1700

Data Index: 61715 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 5.2295. Min Range: -5.2295

Max Act: 5.2295. Min Act: -0.1700

Data Index: 777458 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 5.2295. Min Range: -5.2295

Max Act: 5.1982. Min Act: -0.1700

Data Index: 1329181 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 5.2295. Min Range: -5.2295

Max Act: 5.1357. Min Act: -0.1700

Data Index: 209183 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 5.2295. Min Range: -5.2295

Max Act: 5.1357. Min Act: -0.1700

Data Index: 1142263 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 5.2295. Min Range: -5.2295

Max Act: 5.0732. Min Act: -0.1700

Data Index: 531124 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 5.2295. Min Range: -5.2295

Max Act: 5.0107. Min Act: -0.1700

Data Index: 982424 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 5.2295. Min Range: -5.2295

Max Act: 4.9795. Min Act: -0.1700

Data Index: 669578 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 5.2295. Min Range: -5.2295

Max Act: 5.0107. Min Act: -0.1700

Data Index: 536161 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 5.2295. Min Range: -5.2295

Max Act: 4.9795. Min Act: -0.1700

Data Index: 1068516 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 5.2295. Min Range: -5.2295

Max Act: 4.9482. Min Act: -0.1700

Data Index: 805457 (C4 (Web Text))

Max Activating Token Index: 959

Text #12

Max Range: 5.2295. Min Range: -5.2295

Max Act: 4.8857. Min Act: -0.1700

Data Index: 1207305 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 5.2295. Min Range: -5.2295

Max Act: 4.8857. Min Act: -0.1700

Data Index: 10739 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 5.2295. Min Range: -5.2295

Max Act: 4.8545. Min Act: -0.1700

Data Index: 645114 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 5.2295. Min Range: -5.2295

Max Act: 4.8857. Min Act: -0.1700

Data Index: 1173715 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 5.2295. Min Range: -5.2295

Max Act: 4.8545. Min Act: -0.1700

Data Index: 229701 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 5.2295. Min Range: -5.2295

Max Act: 4.8545. Min Act: -0.1700

Data Index: 1229951 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 5.2295. Min Range: -5.2295

Max Act: 4.8545. Min Act: -0.1700

Data Index: 1284159 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 5.2295. Min Range: -5.2295

Max Act: 4.8545. Min Act: -0.1700

Data Index: 169828 (C4 (Web Text))

Max Activating Token Index: 113