Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1608 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.9192. Min Range: -5.9192

Max Act: 5.9192. Min Act: -0.1700

Data Index: 90799 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 5.9192. Min Range: -5.9192

Max Act: 5.8255. Min Act: -0.1700

Data Index: 282912 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 5.9192. Min Range: -5.9192

Max Act: 5.8255. Min Act: -0.1700

Data Index: 570651 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 5.9192. Min Range: -5.9192

Max Act: 5.7942. Min Act: -0.1700

Data Index: 1094303 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 5.9192. Min Range: -5.9192

Max Act: 5.7630. Min Act: -0.1700

Data Index: 713283 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 5.9192. Min Range: -5.9192

Max Act: 5.7317. Min Act: -0.1700

Data Index: 273508 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 5.9192. Min Range: -5.9192

Max Act: 5.6067. Min Act: -0.1700

Data Index: 971340 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 5.9192. Min Range: -5.9192

Max Act: 5.5755. Min Act: -0.1700

Data Index: 711616 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 5.9192. Min Range: -5.9192

Max Act: 5.4817. Min Act: -0.1700

Data Index: 390405 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 5.9192. Min Range: -5.9192

Max Act: 5.5130. Min Act: -0.1700

Data Index: 782547 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 5.9192. Min Range: -5.9192

Max Act: 5.5130. Min Act: -0.1700

Data Index: 88967 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 5.9192. Min Range: -5.9192

Max Act: 5.4505. Min Act: -0.1700

Data Index: 328169 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 5.9192. Min Range: -5.9192

Max Act: 5.4505. Min Act: -0.1700

Data Index: 436793 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 5.9192. Min Range: -5.9192

Max Act: 5.4192. Min Act: -0.1700

Data Index: 1267188 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 5.9192. Min Range: -5.9192

Max Act: 5.4505. Min Act: -0.1700

Data Index: 597581 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 5.9192. Min Range: -5.9192

Max Act: 5.4505. Min Act: -0.1700

Data Index: 461285 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 5.9192. Min Range: -5.9192

Max Act: 5.3880. Min Act: -0.1700

Data Index: 27704 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 5.9192. Min Range: -5.9192

Max Act: 5.3880. Min Act: -0.1700

Data Index: 154372 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 5.9192. Min Range: -5.9192

Max Act: 5.4192. Min Act: -0.1700

Data Index: 161714 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 5.9192. Min Range: -5.9192

Max Act: 5.4192. Min Act: -0.1700

Data Index: 765534 (C4 (Web Text))

Max Activating Token Index: 248