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

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

Neuron 268 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: 3.1059. Min Range: -3.1059

Max Act: 3.1059. Min Act: -0.1700

Data Index: 1068261 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 3.1059. Min Range: -3.1059

Max Act: 3.0427. Min Act: -0.1700

Data Index: 1319127 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 3.1059. Min Range: -3.1059

Max Act: 3.0427. Min Act: -0.1700

Data Index: 359540 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 3.1059. Min Range: -3.1059

Max Act: 3.0112. Min Act: -0.1700

Data Index: 76818 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 3.1059. Min Range: -3.1059

Max Act: 2.9795. Min Act: -0.1700

Data Index: 706341 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 3.1059. Min Range: -3.1059

Max Act: 2.9637. Min Act: -0.1700

Data Index: 502533 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 3.1059. Min Range: -3.1059

Max Act: 2.9795. Min Act: -0.1700

Data Index: 1152084 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 3.1059. Min Range: -3.1059

Max Act: 2.9637. Min Act: -0.1700

Data Index: 977859 (C4 (Web Text))

Max Activating Token Index: 584

Text #8

Max Range: 3.1059. Min Range: -3.1059

Max Act: 2.9637. Min Act: -0.1700

Data Index: 1013431 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 3.1059. Min Range: -3.1059

Max Act: 2.9637. Min Act: -0.1700

Data Index: 493968 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 3.1059. Min Range: -3.1059

Max Act: 2.9479. Min Act: -0.1700

Data Index: 932176 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 3.1059. Min Range: -3.1059

Max Act: 2.9637. Min Act: -0.1700

Data Index: 70341 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 3.1059. Min Range: -3.1059

Max Act: 2.9479. Min Act: -0.1700

Data Index: 229140 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 3.1059. Min Range: -3.1059

Max Act: 2.9320. Min Act: -0.1700

Data Index: 658579 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 3.1059. Min Range: -3.1059

Max Act: 2.9320. Min Act: -0.1700

Data Index: 67108 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 3.1059. Min Range: -3.1059

Max Act: 2.9320. Min Act: -0.1700

Data Index: 1159233 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 3.1059. Min Range: -3.1059

Max Act: 2.9162. Min Act: -0.1700

Data Index: 1210021 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 3.1059. Min Range: -3.1059

Max Act: 2.9320. Min Act: -0.1700

Data Index: 276903 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 3.1059. Min Range: -3.1059

Max Act: 2.9320. Min Act: -0.1700

Data Index: 1279242 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 3.1059. Min Range: -3.1059

Max Act: 2.9320. Min Act: -0.1700

Data Index: 602250 (C4 (Web Text))

Max Activating Token Index: 66