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

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

Neuron 1144 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4549. Min Range: -5.4549

Max Act: 5.4549. Min Act: -0.1700

Data Index: 1156774 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 5.4549. Min Range: -5.4549

Max Act: 5.3612. Min Act: -0.1700

Data Index: 1285760 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 5.4549. Min Range: -5.4549

Max Act: 5.3612. Min Act: -0.1700

Data Index: 115586 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 5.4549. Min Range: -5.4549

Max Act: 5.3299. Min Act: -0.1700

Data Index: 1148275 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 5.4549. Min Range: -5.4549

Max Act: 5.3299. Min Act: -0.1700

Data Index: 1260278 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 5.4549. Min Range: -5.4549

Max Act: 5.3299. Min Act: -0.1700

Data Index: 1196130 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 5.4549. Min Range: -5.4549

Max Act: 5.3299. Min Act: -0.1700

Data Index: 404449 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 5.4549. Min Range: -5.4549

Max Act: 5.3612. Min Act: -0.1700

Data Index: 1057088 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 5.4549. Min Range: -5.4549

Max Act: 5.2987. Min Act: -0.1700

Data Index: 67943 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 5.4549. Min Range: -5.4549

Max Act: 5.3299. Min Act: -0.1700

Data Index: 957835 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 5.4549. Min Range: -5.4549

Max Act: 5.3299. Min Act: -0.1700

Data Index: 159990 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 5.4549. Min Range: -5.4549

Max Act: 5.2987. Min Act: -0.1700

Data Index: 1319464 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 5.4549. Min Range: -5.4549

Max Act: 5.2987. Min Act: -0.1700

Data Index: 1166719 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 5.4549. Min Range: -5.4549

Max Act: 5.3299. Min Act: -0.1700

Data Index: 342598 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 5.4549. Min Range: -5.4549

Max Act: 5.3299. Min Act: -0.1700

Data Index: 941293 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 5.4549. Min Range: -5.4549

Max Act: 5.2987. Min Act: -0.1700

Data Index: 234536 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 5.4549. Min Range: -5.4549

Max Act: 5.2987. Min Act: -0.1700

Data Index: 404134 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 5.4549. Min Range: -5.4549

Max Act: 5.2674. Min Act: -0.1700

Data Index: 1094500 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 5.4549. Min Range: -5.4549

Max Act: 5.2674. Min Act: -0.1700

Data Index: 1208556 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 5.4549. Min Range: -5.4549

Max Act: 5.2674. Min Act: -0.1700

Data Index: 1253879 (C4 (Web Text))

Max Activating Token Index: 447