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

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

Neuron 1605 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4160. Min Range: -3.4160

Max Act: 3.4160. Min Act: -0.1700

Data Index: 929847 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 3.4160. Min Range: -3.4160

Max Act: 3.2747. Min Act: -0.1700

Data Index: 114968 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 3.4160. Min Range: -3.4160

Max Act: 3.2590. Min Act: -0.1700

Data Index: 1350443 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 3.4160. Min Range: -3.4160

Max Act: 3.2747. Min Act: -0.1700

Data Index: 2847 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 3.4160. Min Range: -3.4160

Max Act: 3.2590. Min Act: -0.1700

Data Index: 800118 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 3.4160. Min Range: -3.4160

Max Act: 3.2433. Min Act: -0.1700

Data Index: 830165 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 3.4160. Min Range: -3.4160

Max Act: 3.2276. Min Act: -0.1700

Data Index: 1218250 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 3.4160. Min Range: -3.4160

Max Act: 3.2276. Min Act: -0.1700

Data Index: 1151264 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 3.4160. Min Range: -3.4160

Max Act: 3.2276. Min Act: -0.1700

Data Index: 788851 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 3.4160. Min Range: -3.4160

Max Act: 3.1961. Min Act: -0.1700

Data Index: 1307938 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 3.4160. Min Range: -3.4160

Max Act: 3.2118. Min Act: -0.1700

Data Index: 794173 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 3.4160. Min Range: -3.4160

Max Act: 3.2118. Min Act: -0.1700

Data Index: 600154 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 3.4160. Min Range: -3.4160

Max Act: 3.2276. Min Act: -0.1700

Data Index: 723630 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 3.4160. Min Range: -3.4160

Max Act: 3.2276. Min Act: -0.1700

Data Index: 188755 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 3.4160. Min Range: -3.4160

Max Act: 3.2276. Min Act: -0.1700

Data Index: 341891 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 3.4160. Min Range: -3.4160

Max Act: 3.2118. Min Act: -0.1700

Data Index: 861812 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 3.4160. Min Range: -3.4160

Max Act: 3.1961. Min Act: -0.1700

Data Index: 1350289 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 3.4160. Min Range: -3.4160

Max Act: 3.1961. Min Act: -0.1700

Data Index: 1195689 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 3.4160. Min Range: -3.4160

Max Act: 3.1961. Min Act: -0.1700

Data Index: 694639 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 3.4160. Min Range: -3.4160

Max Act: 3.1804. Min Act: -0.1700

Data Index: 384211 (C4 (Web Text))

Max Activating Token Index: 989