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

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

Neuron 1190 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3043. Min Range: -5.3043

Max Act: 5.3043. Min Act: -0.1700

Data Index: 789644 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 5.3043. Min Range: -5.3043

Max Act: 5.2731. Min Act: -0.1700

Data Index: 1036982 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 5.3043. Min Range: -5.3043

Max Act: 5.2418. Min Act: -0.1700

Data Index: 1071365 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 5.3043. Min Range: -5.3043

Max Act: 5.2106. Min Act: -0.1700

Data Index: 833360 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 5.3043. Min Range: -5.3043

Max Act: 5.1793. Min Act: -0.1700

Data Index: 908266 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 5.3043. Min Range: -5.3043

Max Act: 5.2106. Min Act: -0.1700

Data Index: 649435 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 5.3043. Min Range: -5.3043

Max Act: 5.1793. Min Act: -0.1700

Data Index: 524771 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 5.3043. Min Range: -5.3043

Max Act: 5.1481. Min Act: -0.1700

Data Index: 317850 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 5.3043. Min Range: -5.3043

Max Act: 5.1168. Min Act: -0.1700

Data Index: 188127 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 5.3043. Min Range: -5.3043

Max Act: 5.0856. Min Act: -0.1700

Data Index: 100074 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 5.3043. Min Range: -5.3043

Max Act: 5.0543. Min Act: -0.1698

Data Index: 97858 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 5.3043. Min Range: -5.3043

Max Act: 5.0231. Min Act: -0.1699

Data Index: 263050 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 5.3043. Min Range: -5.3043

Max Act: 5.0231. Min Act: -0.1700

Data Index: 611257 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 5.3043. Min Range: -5.3043

Max Act: 4.9918. Min Act: -0.1700

Data Index: 859378 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 5.3043. Min Range: -5.3043

Max Act: 4.9918. Min Act: -0.1700

Data Index: 97210 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 5.3043. Min Range: -5.3043

Max Act: 4.9918. Min Act: -0.1700

Data Index: 530706 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 5.3043. Min Range: -5.3043

Max Act: 5.0231. Min Act: -0.1700

Data Index: 293506 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 5.3043. Min Range: -5.3043

Max Act: 4.9606. Min Act: -0.1700

Data Index: 1151556 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 5.3043. Min Range: -5.3043

Max Act: 4.9606. Min Act: -0.1700

Data Index: 512898 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 5.3043. Min Range: -5.3043

Max Act: 4.9293. Min Act: -0.1700

Data Index: 314543 (C4 (Web Text))

Max Activating Token Index: 444