Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1226 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.0067. Min Range: -3.0067

Max Act: 3.0067. Min Act: -0.1700

Data Index: 944562 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.8332. Min Act: -0.1700

Data Index: 1334186 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.8346. Min Act: -0.1700

Data Index: 86726 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.8037. Min Act: -0.1700

Data Index: 1201336 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.8009. Min Act: -0.1700

Data Index: 27046 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.7857. Min Act: -0.1700

Data Index: 1135265 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.8105. Min Act: -0.1699

Data Index: 981173 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.7231. Min Act: -0.1693

Data Index: 1388361 (Python Code)

Max Activating Token Index: 511

Text #8

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.7278. Min Act: -0.1700

Data Index: 176180 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.7259. Min Act: -0.1700

Data Index: 1031271 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.7511. Min Act: -0.1663

Data Index: 192507 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.7450. Min Act: -0.1697

Data Index: 928594 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.7160. Min Act: -0.1699

Data Index: 603483 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.7378. Min Act: -0.1700

Data Index: 1170168 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.7181. Min Act: -0.1700

Data Index: 528276 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.6878. Min Act: -0.1635

Data Index: 1634683 (Python Code)

Max Activating Token Index: 625

Text #16

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.6962. Min Act: -0.1700

Data Index: 1494 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.7110. Min Act: -0.1700

Data Index: 165871 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.7277. Min Act: -0.1700

Data Index: 44251 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.7181. Min Act: -0.1700

Data Index: 240598 (C4 (Web Text))

Max Activating Token Index: 733