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

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

Neuron 1147 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: 3.3898. Min Range: -3.3898

Max Act: 3.3898. Min Act: -0.1700

Data Index: 826167 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.3647. Min Act: -0.1700

Data Index: 364018 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.3576. Min Act: -0.1700

Data Index: 83834 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.3472. Min Act: -0.1700

Data Index: 1164409 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.3273. Min Act: -0.1700

Data Index: 1486265 (Python Code)

Max Activating Token Index: 923

Text #5

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.3270. Min Act: -0.1700

Data Index: 1475567 (Python Code)

Max Activating Token Index: 456

Text #6

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.3157. Min Act: -0.1700

Data Index: 1593369 (Python Code)

Max Activating Token Index: 940

Text #7

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.3325. Min Act: -0.1700

Data Index: 740836 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.2999. Min Act: -0.1700

Data Index: 1388266 (Python Code)

Max Activating Token Index: 362

Text #9

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.2781. Min Act: -0.1700

Data Index: 1369302 (Python Code)

Max Activating Token Index: 308

Text #10

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.2780. Min Act: -0.1700

Data Index: 1595287 (Python Code)

Max Activating Token Index: 961

Text #11

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.2806. Min Act: -0.1700

Data Index: 1574208 (Python Code)

Max Activating Token Index: 966

Text #12

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.2765. Min Act: -0.1700

Data Index: 1640719 (Python Code)

Max Activating Token Index: 802

Text #13

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.2618. Min Act: -0.1700

Data Index: 1439176 (Python Code)

Max Activating Token Index: 978

Text #14

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.2519. Min Act: -0.1700

Data Index: 1463991 (Python Code)

Max Activating Token Index: 474

Text #15

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.2538. Min Act: -0.1700

Data Index: 36755 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.2517. Min Act: -0.1700

Data Index: 558860 (C4 (Web Text))

Max Activating Token Index: 129

Text #17

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.2569. Min Act: -0.1700

Data Index: 1364832 (Python Code)

Max Activating Token Index: 478

Text #18

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.2369. Min Act: -0.1700

Data Index: 620965 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.2303. Min Act: -0.1700

Data Index: 1404752 (Python Code)

Max Activating Token Index: 412