Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 837 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.6448. Min Range: -3.6448

Max Act: 3.6448. Min Act: -0.1700

Data Index: 1006336 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 3.6448. Min Range: -3.6448

Max Act: 3.5822. Min Act: -0.1700

Data Index: 786568 (C4 (Web Text))

Max Activating Token Index: 877

Text #2

Max Range: 3.6448. Min Range: -3.6448

Max Act: 3.4882. Min Act: -0.1700

Data Index: 59333 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 3.6448. Min Range: -3.6448

Max Act: 3.4725. Min Act: -0.1700

Data Index: 495198 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 3.6448. Min Range: -3.6448

Max Act: 3.4255. Min Act: -0.1700

Data Index: 892515 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 3.6448. Min Range: -3.6448

Max Act: 3.4569. Min Act: -0.1700

Data Index: 621502 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 3.6448. Min Range: -3.6448

Max Act: 3.3941. Min Act: -0.1700

Data Index: 96007 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 3.6448. Min Range: -3.6448

Max Act: 3.3941. Min Act: -0.1700

Data Index: 1193788 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 3.6448. Min Range: -3.6448

Max Act: 3.4412. Min Act: -0.1700

Data Index: 197354 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 3.6448. Min Range: -3.6448

Max Act: 3.3785. Min Act: -0.1700

Data Index: 1250555 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 3.6448. Min Range: -3.6448

Max Act: 3.3941. Min Act: -0.1700

Data Index: 707330 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 3.6448. Min Range: -3.6448

Max Act: 3.3785. Min Act: -0.1700

Data Index: 1092069 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 3.6448. Min Range: -3.6448

Max Act: 3.3785. Min Act: -0.1700

Data Index: 1334102 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 3.6448. Min Range: -3.6448

Max Act: 3.3628. Min Act: -0.1700

Data Index: 814539 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 3.6448. Min Range: -3.6448

Max Act: 3.3628. Min Act: -0.1700

Data Index: 183971 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 3.6448. Min Range: -3.6448

Max Act: 3.3628. Min Act: -0.1700

Data Index: 72074 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 3.6448. Min Range: -3.6448

Max Act: 3.3314. Min Act: -0.1700

Data Index: 782310 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 3.6448. Min Range: -3.6448

Max Act: 3.3628. Min Act: -0.1700

Data Index: 160076 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 3.6448. Min Range: -3.6448

Max Act: 3.2843. Min Act: -0.1700

Data Index: 1036726 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 3.6448. Min Range: -3.6448

Max Act: 3.3157. Min Act: -0.1700

Data Index: 507177 (C4 (Web Text))

Max Activating Token Index: 773