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

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

Neuron 76 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: 3.0100. Min Range: -3.0100

Max Act: 3.0100. Min Act: -0.1700

Data Index: 462048 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 3.0100. Min Range: -3.0100

Max Act: 3.0060. Min Act: -0.1700

Data Index: 1090159 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 3.0100. Min Range: -3.0100

Max Act: 2.9574. Min Act: -0.1700

Data Index: 479111 (C4 (Web Text))

Max Activating Token Index: 1018

Text #3

Max Range: 3.0100. Min Range: -3.0100

Max Act: 2.9407. Min Act: -0.1700

Data Index: 1182918 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 3.0100. Min Range: -3.0100

Max Act: 2.9586. Min Act: -0.1700

Data Index: 206257 (C4 (Web Text))

Max Activating Token Index: 561

Text #5

Max Range: 3.0100. Min Range: -3.0100

Max Act: 2.9444. Min Act: -0.1700

Data Index: 551843 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 3.0100. Min Range: -3.0100

Max Act: 2.9488. Min Act: -0.1700

Data Index: 1281146 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 3.0100. Min Range: -3.0100

Max Act: 2.9587. Min Act: -0.1700

Data Index: 1010123 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 3.0100. Min Range: -3.0100

Max Act: 2.9400. Min Act: -0.1700

Data Index: 1338201 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 3.0100. Min Range: -3.0100

Max Act: 2.9609. Min Act: -0.1700

Data Index: 1251711 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 3.0100. Min Range: -3.0100

Max Act: 2.9491. Min Act: -0.1700

Data Index: 923845 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 3.0100. Min Range: -3.0100

Max Act: 2.9537. Min Act: -0.1700

Data Index: 1349442 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 3.0100. Min Range: -3.0100

Max Act: 2.9196. Min Act: -0.1700

Data Index: 785070 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 3.0100. Min Range: -3.0100

Max Act: 2.9171. Min Act: -0.1700

Data Index: 517201 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 3.0100. Min Range: -3.0100

Max Act: 2.9126. Min Act: -0.1700

Data Index: 781409 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 3.0100. Min Range: -3.0100

Max Act: 2.9221. Min Act: -0.1700

Data Index: 863347 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 3.0100. Min Range: -3.0100

Max Act: 2.9326. Min Act: -0.1700

Data Index: 699359 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 3.0100. Min Range: -3.0100

Max Act: 2.9242. Min Act: -0.1700

Data Index: 647629 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 3.0100. Min Range: -3.0100

Max Act: 2.9026. Min Act: -0.1700

Data Index: 938300 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 3.0100. Min Range: -3.0100

Max Act: 2.9175. Min Act: -0.1700

Data Index: 857481 (C4 (Web Text))

Max Activating Token Index: 383