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

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

Neuron 490 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: 3.3086. Min Range: -3.3086

Max Act: 3.3086. Min Act: -0.1700

Data Index: 378537 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.2929. Min Act: -0.1700

Data Index: 301750 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.2929. Min Act: -0.1700

Data Index: 938176 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.2615. Min Act: -0.1700

Data Index: 510670 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.2615. Min Act: -0.1700

Data Index: 513768 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.2458. Min Act: -0.1700

Data Index: 999896 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.2458. Min Act: -0.1700

Data Index: 833605 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.2615. Min Act: -0.1700

Data Index: 1127379 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.2458. Min Act: -0.1700

Data Index: 299025 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.2301. Min Act: -0.1700

Data Index: 1189087 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.2301. Min Act: -0.1700

Data Index: 446063 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.2301. Min Act: -0.1700

Data Index: 770092 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.2301. Min Act: -0.1700

Data Index: 1238519 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.2301. Min Act: -0.1700

Data Index: 223017 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.1829. Min Act: -0.1700

Data Index: 199827 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.2143. Min Act: -0.1700

Data Index: 945076 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.1986. Min Act: -0.1700

Data Index: 164842 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.1829. Min Act: -0.1700

Data Index: 45511 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.2143. Min Act: -0.1700

Data Index: 898068 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 3.3086. Min Range: -3.3086

Max Act: 3.1829. Min Act: -0.1700

Data Index: 600035 (C4 (Web Text))

Max Activating Token Index: 812