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

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

Neuron 300 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2796. Min Range: -3.2796

Max Act: 3.2796. Min Act: -0.1700

Data Index: 1357809 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 3.2796. Min Range: -3.2796

Max Act: 3.2481. Min Act: -0.1700

Data Index: 1329030 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 3.2796. Min Range: -3.2796

Max Act: 3.2324. Min Act: -0.1700

Data Index: 472412 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 3.2796. Min Range: -3.2796

Max Act: 3.2481. Min Act: -0.1700

Data Index: 1016300 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 3.2796. Min Range: -3.2796

Max Act: 3.2481. Min Act: -0.1700

Data Index: 1088243 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 3.2796. Min Range: -3.2796

Max Act: 3.2481. Min Act: -0.1700

Data Index: 1292365 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 3.2796. Min Range: -3.2796

Max Act: 3.2481. Min Act: -0.1700

Data Index: 571529 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 3.2796. Min Range: -3.2796

Max Act: 3.2481. Min Act: -0.1700

Data Index: 399472 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 3.2796. Min Range: -3.2796

Max Act: 3.2481. Min Act: -0.1700

Data Index: 1358141 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 3.2796. Min Range: -3.2796

Max Act: 3.2324. Min Act: -0.1700

Data Index: 419290 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 3.2796. Min Range: -3.2796

Max Act: 3.2324. Min Act: -0.1700

Data Index: 516 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 3.2796. Min Range: -3.2796

Max Act: 3.2324. Min Act: -0.1700

Data Index: 221608 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 3.2796. Min Range: -3.2796

Max Act: 3.2167. Min Act: -0.1700

Data Index: 439683 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 3.2796. Min Range: -3.2796

Max Act: 3.2324. Min Act: -0.1700

Data Index: 1304796 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 3.2796. Min Range: -3.2796

Max Act: 3.2324. Min Act: -0.1700

Data Index: 617686 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 3.2796. Min Range: -3.2796

Max Act: 3.2324. Min Act: -0.1700

Data Index: 100924 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 3.2796. Min Range: -3.2796

Max Act: 3.2481. Min Act: -0.1700

Data Index: 176990 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 3.2796. Min Range: -3.2796

Max Act: 3.2167. Min Act: -0.1700

Data Index: 648465 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 3.2796. Min Range: -3.2796

Max Act: 3.2324. Min Act: -0.1700

Data Index: 69814 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 3.2796. Min Range: -3.2796

Max Act: 3.2167. Min Act: -0.1700

Data Index: 135903 (C4 (Web Text))

Max Activating Token Index: 745