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

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

Neuron 1970 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7086. Min Range: -5.7086

Max Act: 5.7086. Min Act: -0.1700

Data Index: 672609 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 5.7086. Min Range: -5.7086

Max Act: 5.6461. Min Act: -0.1700

Data Index: 786080 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 5.7086. Min Range: -5.7086

Max Act: 5.5836. Min Act: -0.1700

Data Index: 136653 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 5.7086. Min Range: -5.7086

Max Act: 5.6148. Min Act: -0.1700

Data Index: 222895 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 5.7086. Min Range: -5.7086

Max Act: 5.5836. Min Act: -0.1700

Data Index: 699830 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 5.7086. Min Range: -5.7086

Max Act: 5.4898. Min Act: -0.1700

Data Index: 324954 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 5.7086. Min Range: -5.7086

Max Act: 5.5211. Min Act: -0.1700

Data Index: 657255 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 5.7086. Min Range: -5.7086

Max Act: 5.4273. Min Act: -0.1700

Data Index: 75247 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 5.7086. Min Range: -5.7086

Max Act: 5.4898. Min Act: -0.1700

Data Index: 727953 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 5.7086. Min Range: -5.7086

Max Act: 5.4898. Min Act: -0.1700

Data Index: 520253 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 5.7086. Min Range: -5.7086

Max Act: 5.4586. Min Act: -0.1700

Data Index: 771400 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 5.7086. Min Range: -5.7086

Max Act: 5.4898. Min Act: -0.1700

Data Index: 879272 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 5.7086. Min Range: -5.7086

Max Act: 5.4273. Min Act: -0.1700

Data Index: 436453 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 5.7086. Min Range: -5.7086

Max Act: 5.3961. Min Act: -0.1700

Data Index: 759531 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 5.7086. Min Range: -5.7086

Max Act: 5.4898. Min Act: -0.1700

Data Index: 521140 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 5.7086. Min Range: -5.7086

Max Act: 5.4586. Min Act: -0.1700

Data Index: 97301 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 5.7086. Min Range: -5.7086

Max Act: 5.4273. Min Act: -0.1700

Data Index: 272898 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 5.7086. Min Range: -5.7086

Max Act: 5.3336. Min Act: -0.1700

Data Index: 702341 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 5.7086. Min Range: -5.7086

Max Act: 5.3648. Min Act: -0.1700

Data Index: 365457 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 5.7086. Min Range: -5.7086

Max Act: 5.3336. Min Act: -0.1700

Data Index: 565014 (C4 (Web Text))

Max Activating Token Index: 226