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

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

Neuron 1274 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6986. Min Range: -5.6986

Max Act: 5.6986. Min Act: -0.1700

Data Index: 897109 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 5.6986. Min Range: -5.6986

Max Act: 5.6986. Min Act: -0.1700

Data Index: 285985 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 5.6986. Min Range: -5.6986

Max Act: 5.6361. Min Act: -0.1700

Data Index: 393755 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 5.6986. Min Range: -5.6986

Max Act: 5.5111. Min Act: -0.1700

Data Index: 860224 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 5.6986. Min Range: -5.6986

Max Act: 5.5111. Min Act: -0.1700

Data Index: 543776 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 5.6986. Min Range: -5.6986

Max Act: 5.5423. Min Act: -0.1700

Data Index: 698762 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 5.6986. Min Range: -5.6986

Max Act: 5.4486. Min Act: -0.1699

Data Index: 1114426 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 5.6986. Min Range: -5.6986

Max Act: 5.4486. Min Act: -0.1700

Data Index: 487507 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 5.6986. Min Range: -5.6986

Max Act: 5.5423. Min Act: -0.1700

Data Index: 185613 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 5.6986. Min Range: -5.6986

Max Act: 5.5111. Min Act: -0.1700

Data Index: 248670 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 5.6986. Min Range: -5.6986

Max Act: 5.4798. Min Act: -0.1700

Data Index: 214482 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 5.6986. Min Range: -5.6986

Max Act: 5.4798. Min Act: -0.1700

Data Index: 728667 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 5.6986. Min Range: -5.6986

Max Act: 5.4486. Min Act: -0.1700

Data Index: 633212 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 5.6986. Min Range: -5.6986

Max Act: 5.4173. Min Act: -0.1700

Data Index: 1102011 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 5.6986. Min Range: -5.6986

Max Act: 5.4798. Min Act: -0.1700

Data Index: 986056 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 5.6986. Min Range: -5.6986

Max Act: 5.4173. Min Act: -0.1700

Data Index: 162386 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 5.6986. Min Range: -5.6986

Max Act: 5.3548. Min Act: -0.1700

Data Index: 932116 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 5.6986. Min Range: -5.6986

Max Act: 5.4173. Min Act: -0.1700

Data Index: 913599 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 5.6986. Min Range: -5.6986

Max Act: 5.4173. Min Act: -0.1700

Data Index: 35386 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 5.6986. Min Range: -5.6986

Max Act: 5.3861. Min Act: -0.1700

Data Index: 43729 (C4 (Web Text))

Max Activating Token Index: 343