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

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

Neuron 1336 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.9318. Min Act: -0.1700

Data Index: 414093 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.9005. Min Act: -0.1700

Data Index: 345480 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.9005. Min Act: -0.1700

Data Index: 884272 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.9005. Min Act: -0.1700

Data Index: 1143044 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.9318. Min Act: -0.1700

Data Index: 52286 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.9318. Min Act: -0.1700

Data Index: 472192 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.9005. Min Act: -0.1700

Data Index: 753182 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.8693. Min Act: -0.1700

Data Index: 1213360 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.8380. Min Act: -0.1700

Data Index: 1263087 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.8380. Min Act: -0.1700

Data Index: 1224726 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.8380. Min Act: -0.1700

Data Index: 1059264 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.8067. Min Act: -0.1700

Data Index: 706424 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.8067. Min Act: -0.1700

Data Index: 118943 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.8067. Min Act: -0.1700

Data Index: 416235 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.8067. Min Act: -0.1700

Data Index: 197977 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.8067. Min Act: -0.1700

Data Index: 170936 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.7754. Min Act: -0.1700

Data Index: 943436 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.7441. Min Act: -0.1700

Data Index: 83530 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.7754. Min Act: -0.1700

Data Index: 722245 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 3.9318. Min Range: -3.9318

Max Act: 3.7754. Min Act: -0.1700

Data Index: 354592 (C4 (Web Text))

Max Activating Token Index: 622