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

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

Neuron 1003 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 7.5197. Min Range: -7.5197

Max Act: 7.4884. Min Act: -0.1700

Data Index: 550699 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 7.5197. Min Range: -7.5197

Max Act: 7.5197. Min Act: -0.1700

Data Index: 481738 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 7.5197. Min Range: -7.5197

Max Act: 7.4572. Min Act: -0.1700

Data Index: 824240 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 7.5197. Min Range: -7.5197

Max Act: 7.3947. Min Act: -0.1700

Data Index: 553208 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 7.5197. Min Range: -7.5197

Max Act: 7.4259. Min Act: -0.1700

Data Index: 817228 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 7.5197. Min Range: -7.5197

Max Act: 7.5197. Min Act: -0.1700

Data Index: 115663 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 7.5197. Min Range: -7.5197

Max Act: 7.4259. Min Act: -0.1700

Data Index: 988482 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 7.5197. Min Range: -7.5197

Max Act: 7.4572. Min Act: -0.1700

Data Index: 186683 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 7.5197. Min Range: -7.5197

Max Act: 7.3947. Min Act: -0.1700

Data Index: 1156052 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 7.5197. Min Range: -7.5197

Max Act: 7.3322. Min Act: -0.1700

Data Index: 330675 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 7.5197. Min Range: -7.5197

Max Act: 7.3634. Min Act: -0.1700

Data Index: 356061 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 7.5197. Min Range: -7.5197

Max Act: 7.3009. Min Act: -0.1700

Data Index: 580662 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 7.5197. Min Range: -7.5197

Max Act: 7.2697. Min Act: -0.1700

Data Index: 677302 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 7.5197. Min Range: -7.5197

Max Act: 7.2384. Min Act: -0.1700

Data Index: 912434 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 7.5197. Min Range: -7.5197

Max Act: 7.2697. Min Act: -0.1700

Data Index: 1279502 (C4 (Web Text))

Max Activating Token Index: 947

Text #15

Max Range: 7.5197. Min Range: -7.5197

Max Act: 7.3009. Min Act: -0.1700

Data Index: 868336 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 7.5197. Min Range: -7.5197

Max Act: 7.2384. Min Act: -0.1700

Data Index: 817004 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 7.5197. Min Range: -7.5197

Max Act: 7.2072. Min Act: -0.1700

Data Index: 1099467 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 7.5197. Min Range: -7.5197

Max Act: 7.2072. Min Act: -0.1700

Data Index: 43316 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 7.5197. Min Range: -7.5197

Max Act: 7.2072. Min Act: -0.1700

Data Index: 516143 (C4 (Web Text))

Max Activating Token Index: 559