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

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

Neuron 212 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: 4.3311. Min Range: -4.3311

Max Act: 4.3311. Min Act: -0.1700

Data Index: 1317725 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 4.3311. Min Range: -4.3311

Max Act: 4.1705. Min Act: -0.1700

Data Index: 1050522 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 4.3311. Min Range: -4.3311

Max Act: 4.1403. Min Act: -0.1700

Data Index: 190101 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 4.3311. Min Range: -4.3311

Max Act: 4.1337. Min Act: -0.1700

Data Index: 1061441 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 4.3311. Min Range: -4.3311

Max Act: 4.1195. Min Act: -0.1700

Data Index: 221375 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 4.3311. Min Range: -4.3311

Max Act: 4.0985. Min Act: -0.1700

Data Index: 874535 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 4.3311. Min Range: -4.3311

Max Act: 4.1057. Min Act: -0.1700

Data Index: 819742 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 4.3311. Min Range: -4.3311

Max Act: 4.1101. Min Act: -0.1700

Data Index: 1076737 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 4.3311. Min Range: -4.3311

Max Act: 4.0831. Min Act: -0.1700

Data Index: 38349 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 4.3311. Min Range: -4.3311

Max Act: 4.0699. Min Act: -0.1700

Data Index: 437080 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 4.3311. Min Range: -4.3311

Max Act: 4.0646. Min Act: -0.1700

Data Index: 495943 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 4.3311. Min Range: -4.3311

Max Act: 4.0464. Min Act: -0.1700

Data Index: 73150 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 4.3311. Min Range: -4.3311

Max Act: 4.0447. Min Act: -0.1700

Data Index: 610643 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 4.3311. Min Range: -4.3311

Max Act: 4.0466. Min Act: -0.1700

Data Index: 642734 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 4.3311. Min Range: -4.3311

Max Act: 4.0325. Min Act: -0.1700

Data Index: 578579 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 4.3311. Min Range: -4.3311

Max Act: 4.0143. Min Act: -0.1700

Data Index: 750785 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 4.3311. Min Range: -4.3311

Max Act: 4.0193. Min Act: -0.1700

Data Index: 797771 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 4.3311. Min Range: -4.3311

Max Act: 4.0325. Min Act: -0.1700

Data Index: 316853 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 4.3311. Min Range: -4.3311

Max Act: 4.0041. Min Act: -0.1700

Data Index: 128351 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 4.3311. Min Range: -4.3311

Max Act: 3.9839. Min Act: -0.1700

Data Index: 840527 (C4 (Web Text))

Max Activating Token Index: 562