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

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

Neuron 35 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: 3.3442. Min Range: -3.3442

Max Act: 3.3442. Min Act: -0.1700

Data Index: 1129822 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.1871. Min Act: -0.1700

Data Index: 311490 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.1871. Min Act: -0.1700

Data Index: 272904 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.1241. Min Act: -0.1700

Data Index: 1139066 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.1241. Min Act: -0.1700

Data Index: 1344629 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.0926. Min Act: -0.1700

Data Index: 703999 (C4 (Web Text))

Max Activating Token Index: 608

Text #6

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.0926. Min Act: -0.1700

Data Index: 594552 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.0768. Min Act: -0.1700

Data Index: 690326 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.0610. Min Act: -0.1700

Data Index: 1351174 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.0452. Min Act: -0.1700

Data Index: 1339557 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.0452. Min Act: -0.1700

Data Index: 1151027 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.0768. Min Act: -0.1700

Data Index: 1028742 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.0136. Min Act: -0.1700

Data Index: 1038379 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.0294. Min Act: -0.1700

Data Index: 683038 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.0136. Min Act: -0.1700

Data Index: 551459 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.0452. Min Act: -0.1700

Data Index: 797247 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 3.3442. Min Range: -3.3442

Max Act: 2.9978. Min Act: -0.1700

Data Index: 716278 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 3.3442. Min Range: -3.3442

Max Act: 2.9978. Min Act: -0.1700

Data Index: 170556 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 3.3442. Min Range: -3.3442

Max Act: 2.9978. Min Act: -0.1700

Data Index: 587529 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.0294. Min Act: -0.1700

Data Index: 881367 (C4 (Web Text))

Max Activating Token Index: 793