Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1908 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.5672. Min Act: -0.1700

Data Index: 169130 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.5672. Min Act: -0.1700

Data Index: 1200808 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.5672. Min Act: -0.1700

Data Index: 829299 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.5358. Min Act: -0.1700

Data Index: 171387 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.4732. Min Act: -0.1700

Data Index: 1485436 (Python Code)

Max Activating Token Index: 419

Text #5

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.4104. Min Act: -0.1700

Data Index: 1251354 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.3948. Min Act: -0.1700

Data Index: 1613077 (Python Code)

Max Activating Token Index: 412

Text #7

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.4104. Min Act: -0.1700

Data Index: 797262 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.3791. Min Act: -0.1700

Data Index: 1123536 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.3948. Min Act: -0.1700

Data Index: 1602105 (Python Code)

Max Activating Token Index: 474

Text #10

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.3634. Min Act: -0.1700

Data Index: 752034 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.3791. Min Act: -0.1700

Data Index: 1032297 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.3634. Min Act: -0.1700

Data Index: 1371202 (Python Code)

Max Activating Token Index: 92

Text #13

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.3791. Min Act: -0.1700

Data Index: 1088361 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.3634. Min Act: -0.1700

Data Index: 1147080 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.3634. Min Act: -0.1700

Data Index: 1629462 (Python Code)

Max Activating Token Index: 479

Text #16

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.3477. Min Act: -0.1700

Data Index: 1449877 (Python Code)

Max Activating Token Index: 844

Text #17

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.3320. Min Act: -0.1700

Data Index: 1408474 (Python Code)

Max Activating Token Index: 531

Text #18

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.3477. Min Act: -0.1700

Data Index: 1342655 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 3.5672. Min Range: -3.5672

Max Act: 3.3477. Min Act: -0.1700

Data Index: 924451 (C4 (Web Text))

Max Activating Token Index: 494