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

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

Neuron 984 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: 4.3511. Min Range: -4.3511

Max Act: 4.3511. Min Act: -0.1700

Data Index: 1224516 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 4.3511. Min Range: -4.3511

Max Act: 4.2276. Min Act: -0.1700

Data Index: 1243650 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 4.3511. Min Range: -4.3511

Max Act: 4.1721. Min Act: -0.1700

Data Index: 183104 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 4.3511. Min Range: -4.3511

Max Act: 4.1120. Min Act: -0.1700

Data Index: 1347725 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 4.3511. Min Range: -4.3511

Max Act: 4.1237. Min Act: -0.1700

Data Index: 1151508 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 4.3511. Min Range: -4.3511

Max Act: 4.1338. Min Act: -0.1700

Data Index: 325665 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 4.3511. Min Range: -4.3511

Max Act: 4.0959. Min Act: -0.1700

Data Index: 7573 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 4.3511. Min Range: -4.3511

Max Act: 4.0862. Min Act: -0.1700

Data Index: 108033 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 4.3511. Min Range: -4.3511

Max Act: 4.0716. Min Act: -0.1700

Data Index: 383695 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 4.3511. Min Range: -4.3511

Max Act: 4.0699. Min Act: -0.1700

Data Index: 318610 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 4.3511. Min Range: -4.3511

Max Act: 4.0567. Min Act: -0.1700

Data Index: 1334720 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 4.3511. Min Range: -4.3511

Max Act: 4.0085. Min Act: -0.1700

Data Index: 1082995 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 4.3511. Min Range: -4.3511

Max Act: 4.0358. Min Act: -0.1700

Data Index: 558754 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 4.3511. Min Range: -4.3511

Max Act: 4.0482. Min Act: -0.1700

Data Index: 399955 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 4.3511. Min Range: -4.3511

Max Act: 4.0609. Min Act: -0.1700

Data Index: 206580 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 4.3511. Min Range: -4.3511

Max Act: 4.0200. Min Act: -0.1700

Data Index: 746276 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 4.3511. Min Range: -4.3511

Max Act: 4.0202. Min Act: -0.1700

Data Index: 823008 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 4.3511. Min Range: -4.3511

Max Act: 4.0370. Min Act: -0.1700

Data Index: 1299379 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 4.3511. Min Range: -4.3511

Max Act: 4.0364. Min Act: -0.1700

Data Index: 1342299 (C4 (Web Text))

Max Activating Token Index: 468

Text #19

Max Range: 4.3511. Min Range: -4.3511

Max Act: 4.0250. Min Act: -0.1700

Data Index: 1027724 (C4 (Web Text))

Max Activating Token Index: 366