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

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

Neuron 658 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: 4.4201. Min Range: -4.4201

Max Act: 4.4201. Min Act: -0.1700

Data Index: 1114656 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 4.4201. Min Range: -4.4201

Max Act: 4.3292. Min Act: -0.1700

Data Index: 153005 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 4.4201. Min Range: -4.4201

Max Act: 4.2376. Min Act: -0.1700

Data Index: 810478 (C4 (Web Text))

Max Activating Token Index: 1018

Text #3

Max Range: 4.4201. Min Range: -4.4201

Max Act: 4.1924. Min Act: -0.1700

Data Index: 1184901 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 4.4201. Min Range: -4.4201

Max Act: 4.2039. Min Act: -0.1700

Data Index: 134232 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 4.4201. Min Range: -4.4201

Max Act: 4.2063. Min Act: -0.1700

Data Index: 296078 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 4.4201. Min Range: -4.4201

Max Act: 4.1485. Min Act: -0.1700

Data Index: 92460 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 4.4201. Min Range: -4.4201

Max Act: 4.1749. Min Act: -0.1700

Data Index: 199487 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 4.4201. Min Range: -4.4201

Max Act: 4.1833. Min Act: -0.1700

Data Index: 215771 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 4.4201. Min Range: -4.4201

Max Act: 4.1941. Min Act: -0.1700

Data Index: 537154 (C4 (Web Text))

Max Activating Token Index: 474

Text #10

Max Range: 4.4201. Min Range: -4.4201

Max Act: 4.1765. Min Act: -0.1700

Data Index: 351029 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 4.4201. Min Range: -4.4201

Max Act: 4.1460. Min Act: -0.1700

Data Index: 54797 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 4.4201. Min Range: -4.4201

Max Act: 4.1229. Min Act: -0.1700

Data Index: 545787 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 4.4201. Min Range: -4.4201

Max Act: 4.0732. Min Act: -0.1700

Data Index: 606778 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 4.4201. Min Range: -4.4201

Max Act: 4.1177. Min Act: -0.1700

Data Index: 220387 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 4.4201. Min Range: -4.4201

Max Act: 4.1022. Min Act: -0.1700

Data Index: 547489 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 4.4201. Min Range: -4.4201

Max Act: 4.0947. Min Act: -0.1700

Data Index: 1544561 (Python Code)

Max Activating Token Index: 686

Text #17

Max Range: 4.4201. Min Range: -4.4201

Max Act: 4.1183. Min Act: -0.1700

Data Index: 1183121 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 4.4201. Min Range: -4.4201

Max Act: 4.0491. Min Act: -0.1700

Data Index: 1358900 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 4.4201. Min Range: -4.4201

Max Act: 4.1103. Min Act: -0.1700

Data Index: 598923 (C4 (Web Text))

Max Activating Token Index: 141