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

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

Neuron 1354 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4730. Min Range: -3.4730

Max Act: 3.4730. Min Act: -0.1700

Data Index: 1312354 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 3.4730. Min Range: -3.4730

Max Act: 3.4730. Min Act: -0.1700

Data Index: 773382 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 3.4730. Min Range: -3.4730

Max Act: 3.3946. Min Act: -0.1700

Data Index: 896953 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 3.4730. Min Range: -3.4730

Max Act: 3.3632. Min Act: -0.1700

Data Index: 103719 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 3.4730. Min Range: -3.4730

Max Act: 3.3475. Min Act: -0.1700

Data Index: 662205 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 3.4730. Min Range: -3.4730

Max Act: 3.3161. Min Act: -0.1700

Data Index: 723538 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 3.4730. Min Range: -3.4730

Max Act: 3.3161. Min Act: -0.1700

Data Index: 288319 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 3.4730. Min Range: -3.4730

Max Act: 3.3318. Min Act: -0.1700

Data Index: 853454 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 3.4730. Min Range: -3.4730

Max Act: 3.3475. Min Act: -0.1700

Data Index: 1305496 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 3.4730. Min Range: -3.4730

Max Act: 3.3318. Min Act: -0.1700

Data Index: 136123 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 3.4730. Min Range: -3.4730

Max Act: 3.3318. Min Act: -0.1700

Data Index: 544320 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 3.4730. Min Range: -3.4730

Max Act: 3.3004. Min Act: -0.1700

Data Index: 884877 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 3.4730. Min Range: -3.4730

Max Act: 3.3318. Min Act: -0.1700

Data Index: 871408 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 3.4730. Min Range: -3.4730

Max Act: 3.3161. Min Act: -0.1700

Data Index: 620651 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 3.4730. Min Range: -3.4730

Max Act: 3.3161. Min Act: -0.1700

Data Index: 1447840 (Python Code)

Max Activating Token Index: 451

Text #15

Max Range: 3.4730. Min Range: -3.4730

Max Act: 3.2847. Min Act: -0.1700

Data Index: 783106 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 3.4730. Min Range: -3.4730

Max Act: 3.2690. Min Act: -0.1700

Data Index: 159489 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 3.4730. Min Range: -3.4730

Max Act: 3.2847. Min Act: -0.1700

Data Index: 613550 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 3.4730. Min Range: -3.4730

Max Act: 3.2847. Min Act: -0.1700

Data Index: 891903 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 3.4730. Min Range: -3.4730

Max Act: 3.2847. Min Act: -0.1700

Data Index: 164601 (C4 (Web Text))

Max Activating Token Index: 979