Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 416 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.8151. Min Range: -5.8151

Max Act: 5.8151. Min Act: -0.1700

Data Index: 1330229 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 5.8151. Min Range: -5.8151

Max Act: 5.7213. Min Act: -0.1700

Data Index: 807317 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 5.8151. Min Range: -5.8151

Max Act: 5.6276. Min Act: -0.1700

Data Index: 219230 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 5.8151. Min Range: -5.8151

Max Act: 5.5963. Min Act: -0.1700

Data Index: 60785 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 5.8151. Min Range: -5.8151

Max Act: 5.5026. Min Act: -0.1700

Data Index: 908430 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 5.8151. Min Range: -5.8151

Max Act: 5.4713. Min Act: -0.1700

Data Index: 647645 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 5.8151. Min Range: -5.8151

Max Act: 5.3463. Min Act: -0.1700

Data Index: 40594 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 5.8151. Min Range: -5.8151

Max Act: 5.3151. Min Act: -0.1700

Data Index: 298835 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 5.8151. Min Range: -5.8151

Max Act: 5.3151. Min Act: -0.1700

Data Index: 1129510 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 5.8151. Min Range: -5.8151

Max Act: 5.2838. Min Act: -0.1700

Data Index: 983801 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 5.8151. Min Range: -5.8151

Max Act: 5.3151. Min Act: -0.1700

Data Index: 626885 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 5.8151. Min Range: -5.8151

Max Act: 5.2526. Min Act: -0.1700

Data Index: 82846 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 5.8151. Min Range: -5.8151

Max Act: 5.2526. Min Act: -0.1700

Data Index: 472489 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 5.8151. Min Range: -5.8151

Max Act: 5.2838. Min Act: -0.1700

Data Index: 291133 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 5.8151. Min Range: -5.8151

Max Act: 5.2213. Min Act: -0.1700

Data Index: 1248941 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 5.8151. Min Range: -5.8151

Max Act: 5.2838. Min Act: -0.1700

Data Index: 143302 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 5.8151. Min Range: -5.8151

Max Act: 5.2526. Min Act: -0.1700

Data Index: 380758 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 5.8151. Min Range: -5.8151

Max Act: 5.2213. Min Act: -0.1700

Data Index: 1085935 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 5.8151. Min Range: -5.8151

Max Act: 5.2213. Min Act: -0.1700

Data Index: 1009027 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 5.8151. Min Range: -5.8151

Max Act: 5.1901. Min Act: -0.1700

Data Index: 969679 (C4 (Web Text))

Max Activating Token Index: 442