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

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

Neuron 1109 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3408. Min Range: -3.3408

Max Act: 3.3408. Min Act: -0.1700

Data Index: 543507 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 3.3408. Min Range: -3.3408

Max Act: 3.1679. Min Act: -0.1700

Data Index: 1259436 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 3.3408. Min Range: -3.3408

Max Act: 3.1994. Min Act: -0.1700

Data Index: 249884 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 3.3408. Min Range: -3.3408

Max Act: 3.1522. Min Act: -0.1700

Data Index: 845289 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 3.3408. Min Range: -3.3408

Max Act: 3.1522. Min Act: -0.1700

Data Index: 1061228 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 3.3408. Min Range: -3.3408

Max Act: 3.1207. Min Act: -0.1700

Data Index: 758149 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 3.3408. Min Range: -3.3408

Max Act: 3.1207. Min Act: -0.1700

Data Index: 1179236 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 3.3408. Min Range: -3.3408

Max Act: 3.1207. Min Act: -0.1700

Data Index: 796814 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 3.3408. Min Range: -3.3408

Max Act: 3.1207. Min Act: -0.1700

Data Index: 1265456 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 3.3408. Min Range: -3.3408

Max Act: 3.1207. Min Act: -0.1700

Data Index: 982808 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 3.3408. Min Range: -3.3408

Max Act: 3.0734. Min Act: -0.1700

Data Index: 346630 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 3.3408. Min Range: -3.3408

Max Act: 3.0892. Min Act: -0.1700

Data Index: 446271 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 3.3408. Min Range: -3.3408

Max Act: 3.1364. Min Act: -0.1700

Data Index: 642880 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 3.3408. Min Range: -3.3408

Max Act: 3.1049. Min Act: -0.1700

Data Index: 1090244 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 3.3408. Min Range: -3.3408

Max Act: 3.1679. Min Act: -0.1700

Data Index: 57079 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 3.3408. Min Range: -3.3408

Max Act: 3.0892. Min Act: -0.1700

Data Index: 918581 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 3.3408. Min Range: -3.3408

Max Act: 3.0892. Min Act: -0.1700

Data Index: 55077 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 3.3408. Min Range: -3.3408

Max Act: 3.0576. Min Act: -0.1700

Data Index: 552141 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 3.3408. Min Range: -3.3408

Max Act: 3.0418. Min Act: -0.1700

Data Index: 934973 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 3.3408. Min Range: -3.3408

Max Act: 3.0576. Min Act: -0.1700

Data Index: 970748 (C4 (Web Text))

Max Activating Token Index: 292