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

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

Neuron 1077 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: 7.4340. Min Range: -7.4340

Max Act: 7.4340. Min Act: -0.1700

Data Index: 129630 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 7.4340. Min Range: -7.4340

Max Act: 7.3715. Min Act: -0.1700

Data Index: 771650 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 7.4340. Min Range: -7.4340

Max Act: 7.3715. Min Act: -0.1700

Data Index: 188931 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 7.4340. Min Range: -7.4340

Max Act: 7.3090. Min Act: -0.1700

Data Index: 624548 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 7.4340. Min Range: -7.4340

Max Act: 7.3403. Min Act: -0.1700

Data Index: 436904 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 7.4340. Min Range: -7.4340

Max Act: 7.3403. Min Act: -0.1700

Data Index: 517420 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 7.4340. Min Range: -7.4340

Max Act: 7.2153. Min Act: -0.1700

Data Index: 875059 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 7.4340. Min Range: -7.4340

Max Act: 7.2778. Min Act: -0.1700

Data Index: 484302 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 7.4340. Min Range: -7.4340

Max Act: 7.2465. Min Act: -0.1692

Data Index: 1305953 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 7.4340. Min Range: -7.4340

Max Act: 7.2465. Min Act: -0.1700

Data Index: 1298598 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 7.4340. Min Range: -7.4340

Max Act: 7.2153. Min Act: -0.1700

Data Index: 113240 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 7.4340. Min Range: -7.4340

Max Act: 7.2465. Min Act: -0.1700

Data Index: 63036 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 7.4340. Min Range: -7.4340

Max Act: 7.1840. Min Act: -0.1700

Data Index: 778957 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 7.4340. Min Range: -7.4340

Max Act: 7.1840. Min Act: -0.1700

Data Index: 159559 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 7.4340. Min Range: -7.4340

Max Act: 7.1528. Min Act: -0.1699

Data Index: 134852 (C4 (Web Text))

Max Activating Token Index: 181

Text #15

Max Range: 7.4340. Min Range: -7.4340

Max Act: 7.1840. Min Act: -0.1700

Data Index: 981261 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 7.4340. Min Range: -7.4340

Max Act: 7.1528. Min Act: -0.1700

Data Index: 988224 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 7.4340. Min Range: -7.4340

Max Act: 7.1528. Min Act: -0.1700

Data Index: 772682 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 7.4340. Min Range: -7.4340

Max Act: 7.1840. Min Act: -0.1700

Data Index: 1028024 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 7.4340. Min Range: -7.4340

Max Act: 7.1215. Min Act: -0.1700

Data Index: 87496 (C4 (Web Text))

Max Activating Token Index: 288