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

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

Neuron 538 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: 5.6897. Min Range: -5.6897

Max Act: 5.6897. Min Act: -0.1700

Data Index: 684849 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 5.6897. Min Range: -5.6897

Max Act: 5.4710. Min Act: -0.1700

Data Index: 1272966 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 5.6897. Min Range: -5.6897

Max Act: 5.4397. Min Act: -0.1700

Data Index: 501911 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 5.6897. Min Range: -5.6897

Max Act: 5.4710. Min Act: -0.1700

Data Index: 231956 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 5.6897. Min Range: -5.6897

Max Act: 5.4085. Min Act: -0.1700

Data Index: 963982 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 5.6897. Min Range: -5.6897

Max Act: 5.3459. Min Act: -0.1700

Data Index: 129189 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 5.6897. Min Range: -5.6897

Max Act: 5.2834. Min Act: -0.1700

Data Index: 465242 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 5.6897. Min Range: -5.6897

Max Act: 5.3147. Min Act: -0.1700

Data Index: 1083491 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 5.6897. Min Range: -5.6897

Max Act: 5.2834. Min Act: -0.1700

Data Index: 205872 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 5.6897. Min Range: -5.6897

Max Act: 5.2209. Min Act: -0.1700

Data Index: 80260 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 5.6897. Min Range: -5.6897

Max Act: 5.1897. Min Act: -0.1700

Data Index: 463831 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 5.6897. Min Range: -5.6897

Max Act: 5.1272. Min Act: -0.1700

Data Index: 1356201 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 5.6897. Min Range: -5.6897

Max Act: 5.1584. Min Act: -0.1700

Data Index: 623548 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 5.6897. Min Range: -5.6897

Max Act: 5.1897. Min Act: -0.1700

Data Index: 891488 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 5.6897. Min Range: -5.6897

Max Act: 5.0647. Min Act: -0.1700

Data Index: 1131718 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 5.6897. Min Range: -5.6897

Max Act: 5.0334. Min Act: -0.1700

Data Index: 1295936 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 5.6897. Min Range: -5.6897

Max Act: 5.0959. Min Act: -0.1700

Data Index: 1294723 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 5.6897. Min Range: -5.6897

Max Act: 5.0959. Min Act: -0.1700

Data Index: 564768 (C4 (Web Text))

Max Activating Token Index: 454

Text #18

Max Range: 5.6897. Min Range: -5.6897

Max Act: 5.0959. Min Act: -0.1700

Data Index: 1170263 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 5.6897. Min Range: -5.6897

Max Act: 5.0959. Min Act: -0.1700

Data Index: 1148628 (C4 (Web Text))

Max Activating Token Index: 188