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

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

Neuron 1938 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: 5.6108. Min Range: -5.6108

Max Act: 5.6108. Min Act: -0.1700

Data Index: 646 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 5.6108. Min Range: -5.6108

Max Act: 5.5796. Min Act: -0.1699

Data Index: 40624 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 5.6108. Min Range: -5.6108

Max Act: 5.5171. Min Act: -0.1700

Data Index: 243823 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 5.6108. Min Range: -5.6108

Max Act: 5.5483. Min Act: -0.1699

Data Index: 129207 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 5.6108. Min Range: -5.6108

Max Act: 5.5483. Min Act: -0.1700

Data Index: 537448 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 5.6108. Min Range: -5.6108

Max Act: 5.5171. Min Act: -0.1698

Data Index: 1011339 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 5.6108. Min Range: -5.6108

Max Act: 5.4546. Min Act: -0.1698

Data Index: 956508 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 5.6108. Min Range: -5.6108

Max Act: 5.5171. Min Act: -0.1700

Data Index: 712235 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 5.6108. Min Range: -5.6108

Max Act: 5.4858. Min Act: -0.1699

Data Index: 1177550 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 5.6108. Min Range: -5.6108

Max Act: 5.4233. Min Act: -0.1700

Data Index: 370034 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 5.6108. Min Range: -5.6108

Max Act: 5.3921. Min Act: -0.1700

Data Index: 805046 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 5.6108. Min Range: -5.6108

Max Act: 5.4233. Min Act: -0.1699

Data Index: 880562 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 5.6108. Min Range: -5.6108

Max Act: 5.4858. Min Act: -0.1699

Data Index: 911160 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 5.6108. Min Range: -5.6108

Max Act: 5.4858. Min Act: -0.1699

Data Index: 1342206 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 5.6108. Min Range: -5.6108

Max Act: 5.4546. Min Act: -0.1698

Data Index: 948052 (C4 (Web Text))

Max Activating Token Index: 729

Text #15

Max Range: 5.6108. Min Range: -5.6108

Max Act: 5.3921. Min Act: -0.1699

Data Index: 127587 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 5.6108. Min Range: -5.6108

Max Act: 5.3921. Min Act: -0.1700

Data Index: 962342 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 5.6108. Min Range: -5.6108

Max Act: 5.4546. Min Act: -0.1700

Data Index: 1151962 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 5.6108. Min Range: -5.6108

Max Act: 5.4233. Min Act: -0.1700

Data Index: 529171 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 5.6108. Min Range: -5.6108

Max Act: 5.4233. Min Act: -0.1699

Data Index: 1102674 (C4 (Web Text))

Max Activating Token Index: 196