Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 485 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.8162. Min Range: -3.8162

Max Act: 3.8162. Min Act: -0.1700

Data Index: 673810 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 3.8162. Min Range: -3.8162

Max Act: 3.3149. Min Act: -0.1700

Data Index: 620612 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 3.8162. Min Range: -3.8162

Max Act: 3.2678. Min Act: -0.1700

Data Index: 1316670 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 3.8162. Min Range: -3.8162

Max Act: 3.2835. Min Act: -0.1700

Data Index: 494101 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 3.8162. Min Range: -3.8162

Max Act: 3.2835. Min Act: -0.1700

Data Index: 573638 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 3.8162. Min Range: -3.8162

Max Act: 3.2521. Min Act: -0.1700

Data Index: 350783 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 3.8162. Min Range: -3.8162

Max Act: 3.2678. Min Act: -0.1700

Data Index: 1149724 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 3.8162. Min Range: -3.8162

Max Act: 3.2521. Min Act: -0.1700

Data Index: 112691 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 3.8162. Min Range: -3.8162

Max Act: 3.2364. Min Act: -0.1700

Data Index: 1071083 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 3.8162. Min Range: -3.8162

Max Act: 3.2678. Min Act: -0.1700

Data Index: 1239900 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 3.8162. Min Range: -3.8162

Max Act: 3.2521. Min Act: -0.1700

Data Index: 1304664 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 3.8162. Min Range: -3.8162

Max Act: 3.2521. Min Act: -0.1700

Data Index: 1106188 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 3.8162. Min Range: -3.8162

Max Act: 3.2521. Min Act: -0.1700

Data Index: 320384 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 3.8162. Min Range: -3.8162

Max Act: 3.2207. Min Act: -0.1700

Data Index: 1163208 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 3.8162. Min Range: -3.8162

Max Act: 3.2207. Min Act: -0.1700

Data Index: 257895 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 3.8162. Min Range: -3.8162

Max Act: 3.2364. Min Act: -0.1700

Data Index: 1594 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 3.8162. Min Range: -3.8162

Max Act: 3.2364. Min Act: -0.1700

Data Index: 626281 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 3.8162. Min Range: -3.8162

Max Act: 3.2049. Min Act: -0.1700

Data Index: 759380 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 3.8162. Min Range: -3.8162

Max Act: 3.1892. Min Act: -0.1700

Data Index: 1317986 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 3.8162. Min Range: -3.8162

Max Act: 3.2521. Min Act: -0.1700

Data Index: 1037851 (C4 (Web Text))

Max Activating Token Index: 511