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

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

Neuron 150 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.4724. Min Range: -7.4724

Max Act: 7.4724. Min Act: -0.1700

Data Index: 906034 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 7.4724. Min Range: -7.4724

Max Act: 7.3474. Min Act: -0.1698

Data Index: 792062 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 7.4724. Min Range: -7.4724

Max Act: 7.2224. Min Act: -0.1700

Data Index: 363186 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 7.4724. Min Range: -7.4724

Max Act: 7.1911. Min Act: -0.1700

Data Index: 1177854 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 7.4724. Min Range: -7.4724

Max Act: 7.2536. Min Act: -0.1700

Data Index: 884602 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 7.4724. Min Range: -7.4724

Max Act: 7.1599. Min Act: -0.1700

Data Index: 985636 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 7.4724. Min Range: -7.4724

Max Act: 7.1599. Min Act: -0.1679

Data Index: 1048338 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 7.4724. Min Range: -7.4724

Max Act: 7.0974. Min Act: -0.1700

Data Index: 823439 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 7.4724. Min Range: -7.4724

Max Act: 7.1599. Min Act: -0.1700

Data Index: 467067 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 7.4724. Min Range: -7.4724

Max Act: 7.0974. Min Act: -0.1700

Data Index: 719184 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 7.4724. Min Range: -7.4724

Max Act: 7.0974. Min Act: -0.1700

Data Index: 37009 (C4 (Web Text))

Max Activating Token Index: 659

Text #11

Max Range: 7.4724. Min Range: -7.4724

Max Act: 7.1286. Min Act: -0.1700

Data Index: 81715 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 7.4724. Min Range: -7.4724

Max Act: 7.0661. Min Act: -0.1700

Data Index: 1261264 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 7.4724. Min Range: -7.4724

Max Act: 7.0974. Min Act: -0.1700

Data Index: 807407 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 7.4724. Min Range: -7.4724

Max Act: 7.0349. Min Act: -0.1700

Data Index: 1286339 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 7.4724. Min Range: -7.4724

Max Act: 7.0661. Min Act: -0.1700

Data Index: 1113090 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 7.4724. Min Range: -7.4724

Max Act: 7.0661. Min Act: -0.1700

Data Index: 1141764 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 7.4724. Min Range: -7.4724

Max Act: 7.0036. Min Act: -0.1700

Data Index: 1149315 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 7.4724. Min Range: -7.4724

Max Act: 7.0661. Min Act: -0.1700

Data Index: 465596 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 7.4724. Min Range: -7.4724

Max Act: 7.0349. Min Act: -0.1700

Data Index: 1207970 (C4 (Web Text))

Max Activating Token Index: 819