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

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

Neuron 1267 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: 5.7123. Min Range: -5.7123

Max Act: 5.7123. Min Act: -0.1700

Data Index: 873079 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 5.7123. Min Range: -5.7123

Max Act: 5.5716. Min Act: -0.1700

Data Index: 1064095 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 5.7123. Min Range: -5.7123

Max Act: 5.4779. Min Act: -0.1700

Data Index: 688269 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 5.7123. Min Range: -5.7123

Max Act: 5.4466. Min Act: -0.1700

Data Index: 662311 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 5.7123. Min Range: -5.7123

Max Act: 5.4623. Min Act: -0.1700

Data Index: 258334 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 5.7123. Min Range: -5.7123

Max Act: 5.4310. Min Act: -0.1700

Data Index: 707597 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 5.7123. Min Range: -5.7123

Max Act: 5.4466. Min Act: -0.1700

Data Index: 474110 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 5.7123. Min Range: -5.7123

Max Act: 5.4310. Min Act: -0.1700

Data Index: 1323871 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 5.7123. Min Range: -5.7123

Max Act: 5.4310. Min Act: -0.1700

Data Index: 134600 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 5.7123. Min Range: -5.7123

Max Act: 5.4779. Min Act: -0.1700

Data Index: 730128 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 5.7123. Min Range: -5.7123

Max Act: 5.4310. Min Act: -0.1700

Data Index: 790332 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 5.7123. Min Range: -5.7123

Max Act: 5.4466. Min Act: -0.1700

Data Index: 1319177 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 5.7123. Min Range: -5.7123

Max Act: 5.4154. Min Act: -0.1700

Data Index: 191445 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 5.7123. Min Range: -5.7123

Max Act: 5.3685. Min Act: -0.1700

Data Index: 993557 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 5.7123. Min Range: -5.7123

Max Act: 5.4310. Min Act: -0.1700

Data Index: 954416 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 5.7123. Min Range: -5.7123

Max Act: 5.3998. Min Act: -0.1699

Data Index: 484146 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 5.7123. Min Range: -5.7123

Max Act: 5.3685. Min Act: -0.1700

Data Index: 85148 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 5.7123. Min Range: -5.7123

Max Act: 5.3685. Min Act: -0.1700

Data Index: 251011 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 5.7123. Min Range: -5.7123

Max Act: 5.4310. Min Act: -0.1700

Data Index: 56322 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 5.7123. Min Range: -5.7123

Max Act: 5.4154. Min Act: -0.1700

Data Index: 1229329 (C4 (Web Text))

Max Activating Token Index: 617