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

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

Neuron 1306 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: 3.5299. Min Range: -3.5299

Max Act: 3.5299. Min Act: -0.1700

Data Index: 658493 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.3888. Min Act: -0.1700

Data Index: 1229063 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.3575. Min Act: -0.1700

Data Index: 1225276 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.2632. Min Act: -0.1700

Data Index: 1530175 (Python Code)

Max Activating Token Index: 508

Text #4

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.2003. Min Act: -0.1700

Data Index: 961199 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.2161. Min Act: -0.1700

Data Index: 629889 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.2318. Min Act: -0.1700

Data Index: 868891 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.2161. Min Act: -0.1700

Data Index: 452081 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.2161. Min Act: -0.1700

Data Index: 1261784 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.2161. Min Act: -0.1700

Data Index: 1547888 (Python Code)

Max Activating Token Index: 123

Text #10

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.2318. Min Act: -0.1700

Data Index: 1540049 (Python Code)

Max Activating Token Index: 657

Text #11

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.1689. Min Act: -0.1700

Data Index: 703990 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.2003. Min Act: -0.1700

Data Index: 1188158 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.1216. Min Act: -0.1700

Data Index: 47316 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.1846. Min Act: -0.1700

Data Index: 669854 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.2475. Min Act: -0.1700

Data Index: 1231221 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.2003. Min Act: -0.1700

Data Index: 1209808 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.2003. Min Act: -0.1700

Data Index: 421867 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.2161. Min Act: -0.1700

Data Index: 1081717 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.1689. Min Act: -0.1700

Data Index: 568281 (C4 (Web Text))

Max Activating Token Index: 423