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

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

Neuron 1092 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5749. Min Range: -3.5749

Max Act: 3.5749. Min Act: -0.1700

Data Index: 1586384 (Python Code)

Max Activating Token Index: 409

Text #1

Max Range: 3.5749. Min Range: -3.5749

Max Act: 3.5122. Min Act: -0.1700

Data Index: 167415 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 3.5749. Min Range: -3.5749

Max Act: 3.4809. Min Act: -0.1700

Data Index: 1245985 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 3.5749. Min Range: -3.5749

Max Act: 3.4495. Min Act: -0.1700

Data Index: 1123341 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 3.5749. Min Range: -3.5749

Max Act: 3.4339. Min Act: -0.1700

Data Index: 1235774 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 3.5749. Min Range: -3.5749

Max Act: 3.4025. Min Act: -0.1700

Data Index: 444304 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 3.5749. Min Range: -3.5749

Max Act: 3.3711. Min Act: -0.1700

Data Index: 637481 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 3.5749. Min Range: -3.5749

Max Act: 3.3554. Min Act: -0.1700

Data Index: 113345 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 3.5749. Min Range: -3.5749

Max Act: 3.3083. Min Act: -0.1700

Data Index: 799753 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 3.5749. Min Range: -3.5749

Max Act: 3.2769. Min Act: -0.1700

Data Index: 691250 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 3.5749. Min Range: -3.5749

Max Act: 3.2926. Min Act: -0.1700

Data Index: 393462 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 3.5749. Min Range: -3.5749

Max Act: 3.2612. Min Act: -0.1700

Data Index: 1119190 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 3.5749. Min Range: -3.5749

Max Act: 3.2769. Min Act: -0.1700

Data Index: 1063504 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 3.5749. Min Range: -3.5749

Max Act: 3.2612. Min Act: -0.1700

Data Index: 505365 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 3.5749. Min Range: -3.5749

Max Act: 3.2612. Min Act: -0.1700

Data Index: 941486 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 3.5749. Min Range: -3.5749

Max Act: 3.2612. Min Act: -0.1700

Data Index: 106390 (C4 (Web Text))

Max Activating Token Index: 3

Text #16

Max Range: 3.5749. Min Range: -3.5749

Max Act: 3.2455. Min Act: -0.1700

Data Index: 1200471 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 3.5749. Min Range: -3.5749

Max Act: 3.2298. Min Act: -0.1700

Data Index: 1234879 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 3.5749. Min Range: -3.5749

Max Act: 3.2455. Min Act: -0.1700

Data Index: 1142253 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 3.5749. Min Range: -3.5749

Max Act: 3.2298. Min Act: -0.1700

Data Index: 889572 (C4 (Web Text))

Max Activating Token Index: 217