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

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

Neuron 1906 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.3195. Min Act: -0.1700

Data Index: 555238 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.2723. Min Act: -0.1700

Data Index: 916501 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.2723. Min Act: -0.1700

Data Index: 713726 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.2409. Min Act: -0.1700

Data Index: 241328 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.2409. Min Act: -0.1700

Data Index: 638201 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.2252. Min Act: -0.1700

Data Index: 217119 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.2094. Min Act: -0.1700

Data Index: 549266 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.2094. Min Act: -0.1700

Data Index: 1030618 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.2566. Min Act: -0.1700

Data Index: 1177034 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.2252. Min Act: -0.1700

Data Index: 5621 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.2252. Min Act: -0.1700

Data Index: 157835 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.2252. Min Act: -0.1700

Data Index: 519186 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.1937. Min Act: -0.1700

Data Index: 549383 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.2094. Min Act: -0.1700

Data Index: 525447 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.1937. Min Act: -0.1700

Data Index: 1211868 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.1937. Min Act: -0.1700

Data Index: 116425 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.1622. Min Act: -0.1700

Data Index: 485086 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.1780. Min Act: -0.1700

Data Index: 986451 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.1622. Min Act: -0.1700

Data Index: 1078671 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 3.3195. Min Range: -3.3195

Max Act: 3.1780. Min Act: -0.1700

Data Index: 791218 (C4 (Web Text))

Max Activating Token Index: 259