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

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

Neuron 651 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: 3.2450. Min Range: -3.2450

Max Act: 3.2450. Min Act: -0.1700

Data Index: 225595 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 3.2450. Min Range: -3.2450

Max Act: 3.1031. Min Act: -0.1700

Data Index: 544590 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 3.2450. Min Range: -3.2450

Max Act: 3.1211. Min Act: -0.1700

Data Index: 968938 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 3.2450. Min Range: -3.2450

Max Act: 3.0992. Min Act: -0.1699

Data Index: 1149179 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 3.2450. Min Range: -3.2450

Max Act: 3.0973. Min Act: -0.1700

Data Index: 1189706 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 3.2450. Min Range: -3.2450

Max Act: 3.0413. Min Act: -0.1700

Data Index: 418840 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 3.2450. Min Range: -3.2450

Max Act: 3.0258. Min Act: -0.1700

Data Index: 905087 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 3.2450. Min Range: -3.2450

Max Act: 3.0160. Min Act: -0.1700

Data Index: 1302434 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 3.2450. Min Range: -3.2450

Max Act: 3.0255. Min Act: -0.1700

Data Index: 1336537 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 3.2450. Min Range: -3.2450

Max Act: 3.0263. Min Act: -0.1700

Data Index: 811379 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 3.2450. Min Range: -3.2450

Max Act: 3.0304. Min Act: -0.1700

Data Index: 1358089 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 3.2450. Min Range: -3.2450

Max Act: 3.0141. Min Act: -0.1700

Data Index: 250398 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 3.2450. Min Range: -3.2450

Max Act: 3.0024. Min Act: -0.1700

Data Index: 532798 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 3.2450. Min Range: -3.2450

Max Act: 3.0107. Min Act: -0.1700

Data Index: 187982 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 3.2450. Min Range: -3.2450

Max Act: 3.0059. Min Act: -0.1700

Data Index: 869087 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 3.2450. Min Range: -3.2450

Max Act: 3.0040. Min Act: -0.1700

Data Index: 551162 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 3.2450. Min Range: -3.2450

Max Act: 3.0119. Min Act: -0.1700

Data Index: 44931 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 3.2450. Min Range: -3.2450

Max Act: 3.0270. Min Act: -0.1700

Data Index: 933614 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 3.2450. Min Range: -3.2450

Max Act: 3.0193. Min Act: -0.1699

Data Index: 45458 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 3.2450. Min Range: -3.2450

Max Act: 2.9943. Min Act: -0.1700

Data Index: 302710 (C4 (Web Text))

Max Activating Token Index: 770