Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 201 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.8043. Min Range: -3.8043

Max Act: 3.8043. Min Act: -0.1700

Data Index: 421767 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 3.8043. Min Range: -3.8043

Max Act: 3.6791. Min Act: -0.1700

Data Index: 170288 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 3.8043. Min Range: -3.8043

Max Act: 3.6478. Min Act: -0.1700

Data Index: 1100425 (C4 (Web Text))

Max Activating Token Index: 623

Text #3

Max Range: 3.8043. Min Range: -3.8043

Max Act: 3.6478. Min Act: -0.1700

Data Index: 1071645 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 3.8043. Min Range: -3.8043

Max Act: 3.5852. Min Act: -0.1700

Data Index: 1108058 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 3.8043. Min Range: -3.8043

Max Act: 3.5696. Min Act: -0.1700

Data Index: 285396 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 3.8043. Min Range: -3.8043

Max Act: 3.5539. Min Act: -0.1700

Data Index: 212809 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 3.8043. Min Range: -3.8043

Max Act: 3.5382. Min Act: -0.1700

Data Index: 298199 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 3.8043. Min Range: -3.8043

Max Act: 3.5382. Min Act: -0.1700

Data Index: 653112 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 3.8043. Min Range: -3.8043

Max Act: 3.5226. Min Act: -0.1700

Data Index: 1124897 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 3.8043. Min Range: -3.8043

Max Act: 3.5069. Min Act: -0.1700

Data Index: 388904 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 3.8043. Min Range: -3.8043

Max Act: 3.5382. Min Act: -0.1700

Data Index: 1214022 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 3.8043. Min Range: -3.8043

Max Act: 3.5382. Min Act: -0.1700

Data Index: 1284942 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 3.8043. Min Range: -3.8043

Max Act: 3.4912. Min Act: -0.1700

Data Index: 89780 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 3.8043. Min Range: -3.8043

Max Act: 3.5069. Min Act: -0.1700

Data Index: 779202 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 3.8043. Min Range: -3.8043

Max Act: 3.5069. Min Act: -0.1700

Data Index: 78593 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 3.8043. Min Range: -3.8043

Max Act: 3.5069. Min Act: -0.1700

Data Index: 895098 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 3.8043. Min Range: -3.8043

Max Act: 3.5069. Min Act: -0.1700

Data Index: 54030 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 3.8043. Min Range: -3.8043

Max Act: 3.4912. Min Act: -0.1700

Data Index: 705397 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 3.8043. Min Range: -3.8043

Max Act: 3.4912. Min Act: -0.1700

Data Index: 610198 (C4 (Web Text))

Max Activating Token Index: 952