Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1713 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.4792. Min Range: -5.4792

Max Act: 5.4792. Min Act: -0.1700

Data Index: 1219680 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 5.4792. Min Range: -5.4792

Max Act: 5.3854. Min Act: -0.1700

Data Index: 548022 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 5.4792. Min Range: -5.4792

Max Act: 5.3542. Min Act: -0.1700

Data Index: 566097 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 5.4792. Min Range: -5.4792

Max Act: 5.2917. Min Act: -0.1700

Data Index: 1134875 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 5.4792. Min Range: -5.4792

Max Act: 5.3229. Min Act: -0.1700

Data Index: 507963 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 5.4792. Min Range: -5.4792

Max Act: 5.2917. Min Act: -0.1700

Data Index: 195140 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 5.4792. Min Range: -5.4792

Max Act: 5.2917. Min Act: -0.1700

Data Index: 399100 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 5.4792. Min Range: -5.4792

Max Act: 5.2917. Min Act: -0.1700

Data Index: 257106 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 5.4792. Min Range: -5.4792

Max Act: 5.2604. Min Act: -0.1700

Data Index: 893986 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 5.4792. Min Range: -5.4792

Max Act: 5.2917. Min Act: -0.1700

Data Index: 872601 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 5.4792. Min Range: -5.4792

Max Act: 5.3229. Min Act: -0.1700

Data Index: 640118 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 5.4792. Min Range: -5.4792

Max Act: 5.2292. Min Act: -0.1700

Data Index: 433880 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 5.4792. Min Range: -5.4792

Max Act: 5.2604. Min Act: -0.1700

Data Index: 1193264 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 5.4792. Min Range: -5.4792

Max Act: 5.2292. Min Act: -0.1700

Data Index: 708512 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 5.4792. Min Range: -5.4792

Max Act: 5.1979. Min Act: -0.1700

Data Index: 129789 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 5.4792. Min Range: -5.4792

Max Act: 5.2292. Min Act: -0.1700

Data Index: 871271 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 5.4792. Min Range: -5.4792

Max Act: 5.2292. Min Act: -0.1700

Data Index: 422284 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 5.4792. Min Range: -5.4792

Max Act: 5.1979. Min Act: -0.1700

Data Index: 148341 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 5.4792. Min Range: -5.4792

Max Act: 5.1667. Min Act: -0.1700

Data Index: 706892 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 5.4792. Min Range: -5.4792

Max Act: 5.1667. Min Act: -0.1700

Data Index: 362729 (C4 (Web Text))

Max Activating Token Index: 352