Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 119 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 8.3418. Min Range: -8.3418

Max Act: 8.3418. Min Act: -0.1700

Data Index: 48685 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 8.3418. Min Range: -8.3418

Max Act: 8.2168. Min Act: -0.1700

Data Index: 441987 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 8.3418. Min Range: -8.3418

Max Act: 8.1230. Min Act: -0.1700

Data Index: 358580 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 8.3418. Min Range: -8.3418

Max Act: 8.2793. Min Act: -0.1700

Data Index: 335457 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 8.3418. Min Range: -8.3418

Max Act: 8.1543. Min Act: -0.1700

Data Index: 378918 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 8.3418. Min Range: -8.3418

Max Act: 7.9355. Min Act: -0.1700

Data Index: 909809 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 8.3418. Min Range: -8.3418

Max Act: 8.0918. Min Act: -0.1700

Data Index: 168696 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 8.3418. Min Range: -8.3418

Max Act: 8.0918. Min Act: -0.1700

Data Index: 409996 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 8.3418. Min Range: -8.3418

Max Act: 8.0918. Min Act: -0.1700

Data Index: 961381 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 8.3418. Min Range: -8.3418

Max Act: 7.9980. Min Act: -0.1700

Data Index: 346927 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 8.3418. Min Range: -8.3418

Max Act: 7.9980. Min Act: -0.1700

Data Index: 294063 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 8.3418. Min Range: -8.3418

Max Act: 7.9668. Min Act: -0.1700

Data Index: 769286 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 8.3418. Min Range: -8.3418

Max Act: 8.0918. Min Act: -0.1700

Data Index: 333508 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 8.3418. Min Range: -8.3418

Max Act: 8.0918. Min Act: -0.1700

Data Index: 609623 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 8.3418. Min Range: -8.3418

Max Act: 7.9980. Min Act: -0.1700

Data Index: 949072 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 8.3418. Min Range: -8.3418

Max Act: 7.9355. Min Act: -0.1700

Data Index: 311437 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 8.3418. Min Range: -8.3418

Max Act: 7.9043. Min Act: -0.1700

Data Index: 116986 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 8.3418. Min Range: -8.3418

Max Act: 7.9043. Min Act: -0.1699

Data Index: 250393 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 8.3418. Min Range: -8.3418

Max Act: 7.9355. Min Act: -0.1700

Data Index: 35298 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 8.3418. Min Range: -8.3418

Max Act: 7.9355. Min Act: -0.1700

Data Index: 222807 (C4 (Web Text))

Max Activating Token Index: 708