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

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

Neuron 476 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: 5.1482. Min Range: -5.1482

Max Act: 5.1482. Min Act: -0.1700

Data Index: 476386 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 5.1482. Min Range: -5.1482

Max Act: 5.0857. Min Act: -0.1700

Data Index: 70006 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 5.1482. Min Range: -5.1482

Max Act: 5.1170. Min Act: -0.1700

Data Index: 1529196 (Python Code)

Max Activating Token Index: 672

Text #3

Max Range: 5.1482. Min Range: -5.1482

Max Act: 5.0232. Min Act: -0.1700

Data Index: 482301 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 5.1482. Min Range: -5.1482

Max Act: 5.0232. Min Act: -0.1700

Data Index: 658289 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 5.1482. Min Range: -5.1482

Max Act: 5.0232. Min Act: -0.1700

Data Index: 504909 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 5.1482. Min Range: -5.1482

Max Act: 5.0857. Min Act: -0.1700

Data Index: 570738 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 5.1482. Min Range: -5.1482

Max Act: 5.0857. Min Act: -0.1700

Data Index: 1036417 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 5.1482. Min Range: -5.1482

Max Act: 4.9920. Min Act: -0.1700

Data Index: 130366 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 5.1482. Min Range: -5.1482

Max Act: 5.0232. Min Act: -0.1700

Data Index: 49424 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 5.1482. Min Range: -5.1482

Max Act: 5.0545. Min Act: -0.1700

Data Index: 1320056 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 5.1482. Min Range: -5.1482

Max Act: 4.9920. Min Act: -0.1700

Data Index: 1041858 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 5.1482. Min Range: -5.1482

Max Act: 4.9920. Min Act: -0.1700

Data Index: 1039423 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 5.1482. Min Range: -5.1482

Max Act: 4.9607. Min Act: -0.1700

Data Index: 438724 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 5.1482. Min Range: -5.1482

Max Act: 5.0232. Min Act: -0.1700

Data Index: 592191 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 5.1482. Min Range: -5.1482

Max Act: 4.8670. Min Act: -0.1700

Data Index: 878703 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 5.1482. Min Range: -5.1482

Max Act: 4.9607. Min Act: -0.1700

Data Index: 279720 (C4 (Web Text))

Max Activating Token Index: 390

Text #17

Max Range: 5.1482. Min Range: -5.1482

Max Act: 4.9607. Min Act: -0.1700

Data Index: 200940 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 5.1482. Min Range: -5.1482

Max Act: 4.9920. Min Act: -0.1700

Data Index: 89898 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 5.1482. Min Range: -5.1482

Max Act: 4.8982. Min Act: -0.1700

Data Index: 1031759 (C4 (Web Text))

Max Activating Token Index: 264