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

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

Neuron 1167 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3353. Min Range: -3.3353

Max Act: 3.3353. Min Act: -0.1700

Data Index: 880988 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 3.3353. Min Range: -3.3353

Max Act: 3.3039. Min Act: -0.1700

Data Index: 1004019 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 3.3353. Min Range: -3.3353

Max Act: 3.2253. Min Act: -0.1700

Data Index: 359104 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 3.3353. Min Range: -3.3353

Max Act: 3.0994. Min Act: -0.1700

Data Index: 790144 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 3.3353. Min Range: -3.3353

Max Act: 3.0678. Min Act: -0.1700

Data Index: 490291 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 3.3353. Min Range: -3.3353

Max Act: 3.0678. Min Act: -0.1700

Data Index: 884011 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 3.3353. Min Range: -3.3353

Max Act: 3.0362. Min Act: -0.1700

Data Index: 866091 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 3.3353. Min Range: -3.3353

Max Act: 3.0205. Min Act: -0.1700

Data Index: 232563 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 3.3353. Min Range: -3.3353

Max Act: 3.0046. Min Act: -0.1700

Data Index: 1136567 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 3.3353. Min Range: -3.3353

Max Act: 3.0678. Min Act: -0.1700

Data Index: 1270965 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 3.3353. Min Range: -3.3353

Max Act: 3.0520. Min Act: -0.1700

Data Index: 143501 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 3.3353. Min Range: -3.3353

Max Act: 3.0046. Min Act: -0.1700

Data Index: 819278 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 3.3353. Min Range: -3.3353

Max Act: 3.0046. Min Act: -0.1700

Data Index: 457904 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 3.3353. Min Range: -3.3353

Max Act: 2.9888. Min Act: -0.1700

Data Index: 581745 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 3.3353. Min Range: -3.3353

Max Act: 2.9730. Min Act: -0.1700

Data Index: 974418 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 3.3353. Min Range: -3.3353

Max Act: 2.9888. Min Act: -0.1700

Data Index: 376377 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 3.3353. Min Range: -3.3353

Max Act: 3.0205. Min Act: -0.1700

Data Index: 407854 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 3.3353. Min Range: -3.3353

Max Act: 2.9097. Min Act: -0.1700

Data Index: 1090732 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 3.3353. Min Range: -3.3353

Max Act: 3.0520. Min Act: -0.1700

Data Index: 110907 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 3.3353. Min Range: -3.3353

Max Act: 3.0362. Min Act: -0.1700

Data Index: 145331 (C4 (Web Text))

Max Activating Token Index: 431