Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 526 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 16.6687. Min Range: -16.6687

Max Act: 16.6687. Min Act: -0.1700

Data Index: 34057 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 16.6687. Min Range: -16.6687

Max Act: 15.9492. Min Act: -0.1700

Data Index: 483708 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 16.6687. Min Range: -16.6687

Max Act: 15.8805. Min Act: -0.1700

Data Index: 955345 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 16.6687. Min Range: -16.6687

Max Act: 15.7432. Min Act: -0.1700

Data Index: 1423316 (Python Code)

Max Activating Token Index: 76

Text #4

Max Range: 16.6687. Min Range: -16.6687

Max Act: 15.6519. Min Act: -0.1700

Data Index: 1643779 (Python Code)

Max Activating Token Index: 669

Text #5

Max Range: 16.6687. Min Range: -16.6687

Max Act: 15.5720. Min Act: -0.1700

Data Index: 1641948 (Python Code)

Max Activating Token Index: 124

Text #6

Max Range: 16.6687. Min Range: -16.6687

Max Act: 15.5198. Min Act: -0.1700

Data Index: 1483328 (Python Code)

Max Activating Token Index: 817

Text #7

Max Range: 16.6687. Min Range: -16.6687

Max Act: 15.5821. Min Act: -0.1700

Data Index: 1213837 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 16.6687. Min Range: -16.6687

Max Act: 15.3056. Min Act: -0.1700

Data Index: 935352 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 16.6687. Min Range: -16.6687

Max Act: 15.3025. Min Act: -0.1700

Data Index: 1621155 (Python Code)

Max Activating Token Index: 248

Text #10

Max Range: 16.6687. Min Range: -16.6687

Max Act: 15.2808. Min Act: -0.1700

Data Index: 1601263 (Python Code)

Max Activating Token Index: 39

Text #11

Max Range: 16.6687. Min Range: -16.6687

Max Act: 15.2321. Min Act: -0.1699

Data Index: 1439139 (Python Code)

Max Activating Token Index: 144

Text #12

Max Range: 16.6687. Min Range: -16.6687

Max Act: 14.9719. Min Act: -0.1700

Data Index: 1535151 (Python Code)

Max Activating Token Index: 273

Text #13

Max Range: 16.6687. Min Range: -16.6687

Max Act: 14.9975. Min Act: -0.1700

Data Index: 1601652 (Python Code)

Max Activating Token Index: 102

Text #14

Max Range: 16.6687. Min Range: -16.6687

Max Act: 14.8487. Min Act: -0.1700

Data Index: 1044588 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 16.6687. Min Range: -16.6687

Max Act: 14.7352. Min Act: -0.1700

Data Index: 1506777 (Python Code)

Max Activating Token Index: 541

Text #16

Max Range: 16.6687. Min Range: -16.6687

Max Act: 14.7864. Min Act: -0.1700

Data Index: 422235 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 16.6687. Min Range: -16.6687

Max Act: 14.6612. Min Act: -0.1700

Data Index: 1656685 (Python Code)

Max Activating Token Index: 205

Text #18

Max Range: 16.6687. Min Range: -16.6687

Max Act: 14.5714. Min Act: -0.1700

Data Index: 1562696 (Python Code)

Max Activating Token Index: 769

Text #19

Max Range: 16.6687. Min Range: -16.6687

Max Act: 14.5731. Min Act: -0.1700

Data Index: 1556465 (Python Code)

Max Activating Token Index: 85