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

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

Neuron 441 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: 5.1707. Min Range: -5.1707

Max Act: 5.1707. Min Act: -0.1700

Data Index: 1120975 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 5.1707. Min Range: -5.1707

Max Act: 5.1707. Min Act: -0.1700

Data Index: 555375 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 5.1707. Min Range: -5.1707

Max Act: 5.1707. Min Act: -0.1700

Data Index: 605908 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 5.1707. Min Range: -5.1707

Max Act: 5.0144. Min Act: -0.1700

Data Index: 688310 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 5.1707. Min Range: -5.1707

Max Act: 5.0144. Min Act: -0.1700

Data Index: 121066 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 5.1707. Min Range: -5.1707

Max Act: 4.9207. Min Act: -0.1696

Data Index: 34778 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 5.1707. Min Range: -5.1707

Max Act: 4.8582. Min Act: -0.1700

Data Index: 526402 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 5.1707. Min Range: -5.1707

Max Act: 4.8269. Min Act: -0.1700

Data Index: 929527 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 5.1707. Min Range: -5.1707

Max Act: 4.7957. Min Act: -0.1700

Data Index: 1139832 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 5.1707. Min Range: -5.1707

Max Act: 4.7332. Min Act: -0.1699

Data Index: 680321 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 5.1707. Min Range: -5.1707

Max Act: 4.8269. Min Act: -0.1700

Data Index: 682625 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 5.1707. Min Range: -5.1707

Max Act: 4.7644. Min Act: -0.1699

Data Index: 893470 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 5.1707. Min Range: -5.1707

Max Act: 4.8269. Min Act: -0.1700

Data Index: 536328 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 5.1707. Min Range: -5.1707

Max Act: 4.7644. Min Act: -0.1700

Data Index: 284684 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 5.1707. Min Range: -5.1707

Max Act: 4.7957. Min Act: -0.1700

Data Index: 905435 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 5.1707. Min Range: -5.1707

Max Act: 4.7332. Min Act: -0.1700

Data Index: 566686 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 5.1707. Min Range: -5.1707

Max Act: 4.7644. Min Act: -0.1700

Data Index: 456042 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 5.1707. Min Range: -5.1707

Max Act: 4.7957. Min Act: -0.1700

Data Index: 675521 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 5.1707. Min Range: -5.1707

Max Act: 4.7957. Min Act: -0.1700

Data Index: 929497 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 5.1707. Min Range: -5.1707

Max Act: 4.7644. Min Act: -0.1700

Data Index: 587707 (C4 (Web Text))

Max Activating Token Index: 38