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

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

Neuron 174 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7308. Min Range: -5.7308

Max Act: 5.7308. Min Act: -0.1700

Data Index: 199532 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 5.7308. Min Range: -5.7308

Max Act: 5.2152. Min Act: -0.1699

Data Index: 364018 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 5.7308. Min Range: -5.7308

Max Act: 5.2777. Min Act: -0.1700

Data Index: 362299 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 5.7308. Min Range: -5.7308

Max Act: 5.2464. Min Act: -0.1700

Data Index: 919150 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 5.7308. Min Range: -5.7308

Max Act: 5.2464. Min Act: -0.1700

Data Index: 50624 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 5.7308. Min Range: -5.7308

Max Act: 5.1996. Min Act: -0.1700

Data Index: 806948 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 5.7308. Min Range: -5.7308

Max Act: 5.1683. Min Act: -0.1700

Data Index: 83459 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 5.7308. Min Range: -5.7308

Max Act: 5.2464. Min Act: -0.1700

Data Index: 314347 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 5.7308. Min Range: -5.7308

Max Act: 5.1058. Min Act: -0.1700

Data Index: 350835 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 5.7308. Min Range: -5.7308

Max Act: 5.2152. Min Act: -0.1700

Data Index: 1028974 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 5.7308. Min Range: -5.7308

Max Act: 5.0902. Min Act: -0.1700

Data Index: 564295 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 5.7308. Min Range: -5.7308

Max Act: 5.0121. Min Act: -0.1700

Data Index: 399518 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 5.7308. Min Range: -5.7308

Max Act: 5.0589. Min Act: -0.1700

Data Index: 305743 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 5.7308. Min Range: -5.7308

Max Act: 5.0589. Min Act: -0.1700

Data Index: 998814 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 5.7308. Min Range: -5.7308

Max Act: 5.0746. Min Act: -0.1700

Data Index: 1081807 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 5.7308. Min Range: -5.7308

Max Act: 5.0589. Min Act: -0.1700

Data Index: 1116760 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 5.7308. Min Range: -5.7308

Max Act: 5.0902. Min Act: -0.1700

Data Index: 493276 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 5.7308. Min Range: -5.7308

Max Act: 5.0433. Min Act: -0.1700

Data Index: 787297 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 5.7308. Min Range: -5.7308

Max Act: 5.0277. Min Act: -0.1700

Data Index: 1221095 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 5.7308. Min Range: -5.7308

Max Act: 4.9964. Min Act: -0.1700

Data Index: 32895 (C4 (Web Text))

Max Activating Token Index: 881