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

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

Neuron 144 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: 3.8189. Min Range: -3.8189

Max Act: 3.8189. Min Act: -0.1700

Data Index: 1094245 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.7564. Min Act: -0.1700

Data Index: 93180 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.6312. Min Act: -0.1700

Data Index: 253768 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.6312. Min Act: -0.1700

Data Index: 524132 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.5686. Min Act: -0.1700

Data Index: 784926 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.5999. Min Act: -0.1700

Data Index: 658734 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.5686. Min Act: -0.1700

Data Index: 1051810 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.5372. Min Act: -0.1700

Data Index: 517306 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.5216. Min Act: -0.1700

Data Index: 162348 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.5372. Min Act: -0.1700

Data Index: 1151436 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.5372. Min Act: -0.1700

Data Index: 50214 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.5059. Min Act: -0.1700

Data Index: 83056 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.5059. Min Act: -0.1700

Data Index: 367822 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.4902. Min Act: -0.1700

Data Index: 835990 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.4902. Min Act: -0.1700

Data Index: 369252 (C4 (Web Text))

Max Activating Token Index: 237

Text #15

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.5059. Min Act: -0.1700

Data Index: 44967 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.4746. Min Act: -0.1700

Data Index: 489329 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.4746. Min Act: -0.1700

Data Index: 210257 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.4589. Min Act: -0.1700

Data Index: 1036491 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 3.8189. Min Range: -3.8189

Max Act: 3.4902. Min Act: -0.1700

Data Index: 577412 (C4 (Web Text))

Max Activating Token Index: 640