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

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

Neuron 1802 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: 5.6572. Min Range: -5.6572

Max Act: 5.6572. Min Act: -0.1700

Data Index: 1331633 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 5.6572. Min Range: -5.6572

Max Act: 5.6572. Min Act: -0.1700

Data Index: 91066 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 5.6572. Min Range: -5.6572

Max Act: 5.6259. Min Act: -0.1700

Data Index: 758440 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 5.6572. Min Range: -5.6572

Max Act: 5.6572. Min Act: -0.1700

Data Index: 1007190 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 5.6572. Min Range: -5.6572

Max Act: 5.6259. Min Act: -0.1700

Data Index: 1133942 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 5.6572. Min Range: -5.6572

Max Act: 5.6259. Min Act: -0.1700

Data Index: 1105531 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 5.6572. Min Range: -5.6572

Max Act: 5.6259. Min Act: -0.1700

Data Index: 352505 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 5.6572. Min Range: -5.6572

Max Act: 5.5947. Min Act: -0.1700

Data Index: 34469 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 5.6572. Min Range: -5.6572

Max Act: 5.5634. Min Act: -0.1700

Data Index: 580780 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 5.6572. Min Range: -5.6572

Max Act: 5.5009. Min Act: -0.1700

Data Index: 1266524 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 5.6572. Min Range: -5.6572

Max Act: 5.5634. Min Act: -0.1700

Data Index: 741471 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 5.6572. Min Range: -5.6572

Max Act: 5.5634. Min Act: -0.1700

Data Index: 216092 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 5.6572. Min Range: -5.6572

Max Act: 5.5634. Min Act: -0.1700

Data Index: 1114662 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 5.6572. Min Range: -5.6572

Max Act: 5.5322. Min Act: -0.1700

Data Index: 1154634 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 5.6572. Min Range: -5.6572

Max Act: 5.5322. Min Act: -0.1700

Data Index: 379054 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 5.6572. Min Range: -5.6572

Max Act: 5.5634. Min Act: -0.1700

Data Index: 1078352 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 5.6572. Min Range: -5.6572

Max Act: 5.5322. Min Act: -0.1700

Data Index: 1072023 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 5.6572. Min Range: -5.6572

Max Act: 5.5322. Min Act: -0.1700

Data Index: 315167 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 5.6572. Min Range: -5.6572

Max Act: 5.4697. Min Act: -0.1700

Data Index: 959481 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 5.6572. Min Range: -5.6572

Max Act: 5.5322. Min Act: -0.1700

Data Index: 903063 (C4 (Web Text))

Max Activating Token Index: 354