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

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

Neuron 1919 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.5306. Min Range: -5.5306

Max Act: 5.5306. Min Act: -0.1700

Data Index: 663671 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 5.5306. Min Range: -5.5306

Max Act: 5.4368. Min Act: -0.1700

Data Index: 692945 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 5.5306. Min Range: -5.5306

Max Act: 5.4056. Min Act: -0.1700

Data Index: 453111 (C4 (Web Text))

Max Activating Token Index: 681

Text #3

Max Range: 5.5306. Min Range: -5.5306

Max Act: 5.4056. Min Act: -0.1700

Data Index: 386002 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 5.5306. Min Range: -5.5306

Max Act: 5.3743. Min Act: -0.1700

Data Index: 746170 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 5.5306. Min Range: -5.5306

Max Act: 5.4368. Min Act: -0.1700

Data Index: 174766 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 5.5306. Min Range: -5.5306

Max Act: 5.3431. Min Act: -0.1700

Data Index: 1021139 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 5.5306. Min Range: -5.5306

Max Act: 5.2493. Min Act: -0.1700

Data Index: 729789 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 5.5306. Min Range: -5.5306

Max Act: 5.2806. Min Act: -0.1700

Data Index: 588012 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 5.5306. Min Range: -5.5306

Max Act: 5.3118. Min Act: -0.1700

Data Index: 676841 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 5.5306. Min Range: -5.5306

Max Act: 5.1868. Min Act: -0.1700

Data Index: 1191423 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 5.5306. Min Range: -5.5306

Max Act: 5.1556. Min Act: -0.1700

Data Index: 1131083 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 5.5306. Min Range: -5.5306

Max Act: 5.1556. Min Act: -0.1700

Data Index: 375226 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 5.5306. Min Range: -5.5306

Max Act: 5.1243. Min Act: -0.1700

Data Index: 759768 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 5.5306. Min Range: -5.5306

Max Act: 5.0931. Min Act: -0.1700

Data Index: 295813 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 5.5306. Min Range: -5.5306

Max Act: 5.0931. Min Act: -0.1700

Data Index: 482671 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 5.5306. Min Range: -5.5306

Max Act: 5.1556. Min Act: -0.1700

Data Index: 946001 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 5.5306. Min Range: -5.5306

Max Act: 5.1556. Min Act: -0.1700

Data Index: 434827 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 5.5306. Min Range: -5.5306

Max Act: 5.0618. Min Act: -0.1700

Data Index: 12711 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 5.5306. Min Range: -5.5306

Max Act: 5.0931. Min Act: -0.1700

Data Index: 1142470 (C4 (Web Text))

Max Activating Token Index: 467