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

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

Neuron 567 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: 4.1288. Min Range: -4.1288

Max Act: 4.1288. Min Act: -0.1700

Data Index: 1053786 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 4.1288. Min Range: -4.1288

Max Act: 4.0976. Min Act: -0.1699

Data Index: 490402 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 4.1288. Min Range: -4.1288

Max Act: 4.0976. Min Act: -0.1700

Data Index: 95362 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 4.1288. Min Range: -4.1288

Max Act: 4.0976. Min Act: -0.1700

Data Index: 462270 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 4.1288. Min Range: -4.1288

Max Act: 4.1288. Min Act: -0.1700

Data Index: 1023230 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 4.1288. Min Range: -4.1288

Max Act: 4.0663. Min Act: -0.1700

Data Index: 921082 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 4.1288. Min Range: -4.1288

Max Act: 4.0663. Min Act: -0.1700

Data Index: 458736 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 4.1288. Min Range: -4.1288

Max Act: 4.0038. Min Act: -0.1700

Data Index: 532865 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 4.1288. Min Range: -4.1288

Max Act: 4.0351. Min Act: -0.1700

Data Index: 159256 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 4.1288. Min Range: -4.1288

Max Act: 4.0351. Min Act: -0.1700

Data Index: 849344 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 4.1288. Min Range: -4.1288

Max Act: 4.0351. Min Act: -0.1700

Data Index: 1243080 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 4.1288. Min Range: -4.1288

Max Act: 4.0038. Min Act: -0.1700

Data Index: 579704 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 4.1288. Min Range: -4.1288

Max Act: 4.0038. Min Act: -0.1699

Data Index: 1312601 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 4.1288. Min Range: -4.1288

Max Act: 3.9725. Min Act: -0.1700

Data Index: 1203805 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 4.1288. Min Range: -4.1288

Max Act: 4.0038. Min Act: -0.1700

Data Index: 670097 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 4.1288. Min Range: -4.1288

Max Act: 3.9725. Min Act: -0.1700

Data Index: 1328159 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 4.1288. Min Range: -4.1288

Max Act: 4.0351. Min Act: -0.1699

Data Index: 861456 (C4 (Web Text))

Max Activating Token Index: 954

Text #17

Max Range: 4.1288. Min Range: -4.1288

Max Act: 4.0038. Min Act: -0.1700

Data Index: 331968 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 4.1288. Min Range: -4.1288

Max Act: 4.0038. Min Act: -0.1700

Data Index: 463816 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 4.1288. Min Range: -4.1288

Max Act: 3.9413. Min Act: -0.1700

Data Index: 368398 (C4 (Web Text))

Max Activating Token Index: 29