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

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

Neuron 1505 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.8015. Min Range: -7.8015

Max Act: 7.8015. Min Act: -0.1700

Data Index: 1335419 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 7.8015. Min Range: -7.8015

Max Act: 7.3640. Min Act: -0.1700

Data Index: 654108 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 7.8015. Min Range: -7.8015

Max Act: 7.3327. Min Act: -0.1700

Data Index: 358345 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 7.8015. Min Range: -7.8015

Max Act: 7.2702. Min Act: -0.1700

Data Index: 394643 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 7.8015. Min Range: -7.8015

Max Act: 7.2702. Min Act: -0.1700

Data Index: 570415 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 7.8015. Min Range: -7.8015

Max Act: 7.2077. Min Act: -0.1700

Data Index: 318151 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 7.8015. Min Range: -7.8015

Max Act: 7.2077. Min Act: -0.1700

Data Index: 450245 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 7.8015. Min Range: -7.8015

Max Act: 7.2390. Min Act: -0.1700

Data Index: 779933 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 7.8015. Min Range: -7.8015

Max Act: 7.1452. Min Act: -0.1700

Data Index: 951973 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 7.8015. Min Range: -7.8015

Max Act: 7.1765. Min Act: -0.1700

Data Index: 781401 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 7.8015. Min Range: -7.8015

Max Act: 7.0827. Min Act: -0.1700

Data Index: 800871 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 7.8015. Min Range: -7.8015

Max Act: 7.0515. Min Act: -0.1700

Data Index: 577523 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 7.8015. Min Range: -7.8015

Max Act: 7.0515. Min Act: -0.1700

Data Index: 902290 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 7.8015. Min Range: -7.8015

Max Act: 7.0515. Min Act: -0.1700

Data Index: 1125524 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 7.8015. Min Range: -7.8015

Max Act: 7.1140. Min Act: -0.1700

Data Index: 1119416 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 7.8015. Min Range: -7.8015

Max Act: 7.1140. Min Act: -0.1700

Data Index: 521270 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 7.8015. Min Range: -7.8015

Max Act: 7.0515. Min Act: -0.1700

Data Index: 340734 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 7.8015. Min Range: -7.8015

Max Act: 7.0202. Min Act: -0.1700

Data Index: 399401 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 7.8015. Min Range: -7.8015

Max Act: 6.9577. Min Act: -0.1700

Data Index: 855395 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 7.8015. Min Range: -7.8015

Max Act: 6.9890. Min Act: -0.1700

Data Index: 1060989 (C4 (Web Text))

Max Activating Token Index: 210