Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1371 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 4.6250. Min Range: -4.6250

Max Act: 4.6250. Min Act: -0.1698

Data Index: 1372470 (Python Code)

Max Activating Token Index: 267

Text #1

Max Range: 4.6250. Min Range: -4.6250

Max Act: 4.2500. Min Act: -0.1700

Data Index: 1323574 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 4.6250. Min Range: -4.6250

Max Act: 4.2187. Min Act: -0.1699

Data Index: 165014 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 4.6250. Min Range: -4.6250

Max Act: 4.1249. Min Act: -0.1700

Data Index: 1075609 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 4.6250. Min Range: -4.6250

Max Act: 3.9842. Min Act: -0.1700

Data Index: 1439139 (Python Code)

Max Activating Token Index: 805

Text #5

Max Range: 4.6250. Min Range: -4.6250

Max Act: 3.9373. Min Act: -0.1700

Data Index: 1317486 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 4.6250. Min Range: -4.6250

Max Act: 3.9217. Min Act: -0.1700

Data Index: 67941 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 4.6250. Min Range: -4.6250

Max Act: 3.9217. Min Act: -0.1700

Data Index: 229849 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 4.6250. Min Range: -4.6250

Max Act: 3.8904. Min Act: -0.1698

Data Index: 1466298 (Python Code)

Max Activating Token Index: 419

Text #9

Max Range: 4.6250. Min Range: -4.6250

Max Act: 3.8592. Min Act: -0.1700

Data Index: 157390 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 4.6250. Min Range: -4.6250

Max Act: 3.8279. Min Act: -0.1657

Data Index: 1193272 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 4.6250. Min Range: -4.6250

Max Act: 3.7653. Min Act: -0.1700

Data Index: 1273769 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 4.6250. Min Range: -4.6250

Max Act: 3.7497. Min Act: -0.1700

Data Index: 739569 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 4.6250. Min Range: -4.6250

Max Act: 3.7340. Min Act: -0.1700

Data Index: 1604392 (Python Code)

Max Activating Token Index: 204

Text #14

Max Range: 4.6250. Min Range: -4.6250

Max Act: 3.7027. Min Act: -0.1700

Data Index: 112234 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 4.6250. Min Range: -4.6250

Max Act: 3.6714. Min Act: -0.1700

Data Index: 1641948 (Python Code)

Max Activating Token Index: 513

Text #16

Max Range: 4.6250. Min Range: -4.6250

Max Act: 3.6401. Min Act: -0.1700

Data Index: 859023 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 4.6250. Min Range: -4.6250

Max Act: 3.6088. Min Act: -0.1700

Data Index: 690456 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 4.6250. Min Range: -4.6250

Max Act: 3.6088. Min Act: -0.1699

Data Index: 1325933 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 4.6250. Min Range: -4.6250

Max Act: 3.6088. Min Act: -0.1700

Data Index: 1274036 (C4 (Web Text))

Max Activating Token Index: 374