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

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

Neuron 1966 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: 3.6797. Min Range: -3.6797

Max Act: 3.6797. Min Act: -0.1700

Data Index: 175936 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.6641. Min Act: -0.1700

Data Index: 442885 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.6015. Min Act: -0.1699

Data Index: 1151537 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.6015. Min Act: -0.1699

Data Index: 870781 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.6015. Min Act: -0.1700

Data Index: 157483 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5858. Min Act: -0.1700

Data Index: 1060123 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5858. Min Act: -0.1700

Data Index: 814783 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.6015. Min Act: -0.1697

Data Index: 395508 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5702. Min Act: -0.1699

Data Index: 450874 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5702. Min Act: -0.1700

Data Index: 442400 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5702. Min Act: -0.1700

Data Index: 926859 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5702. Min Act: -0.1700

Data Index: 714296 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5388. Min Act: -0.1700

Data Index: 402125 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5545. Min Act: -0.1700

Data Index: 377515 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5232. Min Act: -0.1700

Data Index: 736001 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.4918. Min Act: -0.1700

Data Index: 365517 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.4918. Min Act: -0.1699

Data Index: 202218 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.4448. Min Act: -0.1700

Data Index: 995376 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.4605. Min Act: -0.1700

Data Index: 958808 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.4291. Min Act: -0.1700

Data Index: 588271 (C4 (Web Text))

Max Activating Token Index: 446