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

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

Neuron 1682 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: 5.5714. Min Range: -5.5714

Max Act: 5.5714. Min Act: -0.1700

Data Index: 795418 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 5.5714. Min Range: -5.5714

Max Act: 5.5402. Min Act: -0.1700

Data Index: 1260278 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 5.5714. Min Range: -5.5714

Max Act: 5.5089. Min Act: -0.1700

Data Index: 622024 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 5.5714. Min Range: -5.5714

Max Act: 5.4464. Min Act: -0.1700

Data Index: 773598 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 5.5714. Min Range: -5.5714

Max Act: 5.5089. Min Act: -0.1700

Data Index: 108967 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 5.5714. Min Range: -5.5714

Max Act: 5.4777. Min Act: -0.1700

Data Index: 632653 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 5.5714. Min Range: -5.5714

Max Act: 5.4152. Min Act: -0.1700

Data Index: 928985 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 5.5714. Min Range: -5.5714

Max Act: 5.4777. Min Act: -0.1700

Data Index: 246827 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 5.5714. Min Range: -5.5714

Max Act: 5.4152. Min Act: -0.1700

Data Index: 115586 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 5.5714. Min Range: -5.5714

Max Act: 5.4152. Min Act: -0.1700

Data Index: 794732 (C4 (Web Text))

Max Activating Token Index: 324

Text #10

Max Range: 5.5714. Min Range: -5.5714

Max Act: 5.3839. Min Act: -0.1700

Data Index: 1035225 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 5.5714. Min Range: -5.5714

Max Act: 5.4152. Min Act: -0.1700

Data Index: 961755 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 5.5714. Min Range: -5.5714

Max Act: 5.4464. Min Act: -0.1700

Data Index: 58529 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 5.5714. Min Range: -5.5714

Max Act: 5.3527. Min Act: -0.1700

Data Index: 811337 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 5.5714. Min Range: -5.5714

Max Act: 5.3839. Min Act: -0.1700

Data Index: 1094500 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 5.5714. Min Range: -5.5714

Max Act: 5.3214. Min Act: -0.1700

Data Index: 739496 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 5.5714. Min Range: -5.5714

Max Act: 5.3527. Min Act: -0.1700

Data Index: 266441 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 5.5714. Min Range: -5.5714

Max Act: 5.3214. Min Act: -0.1700

Data Index: 996251 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 5.5714. Min Range: -5.5714

Max Act: 5.3527. Min Act: -0.1700

Data Index: 493550 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 5.5714. Min Range: -5.5714

Max Act: 5.3214. Min Act: -0.1700

Data Index: 281355 (C4 (Web Text))

Max Activating Token Index: 481