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

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

Neuron 301 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: 4.0862. Min Range: -4.0862

Max Act: 4.0862. Min Act: -0.1700

Data Index: 418277 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 4.0862. Min Range: -4.0862

Max Act: 4.0318. Min Act: -0.1700

Data Index: 476566 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 4.0862. Min Range: -4.0862

Max Act: 3.9906. Min Act: -0.1700

Data Index: 19912 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 4.0862. Min Range: -4.0862

Max Act: 3.9655. Min Act: -0.1700

Data Index: 1318846 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 4.0862. Min Range: -4.0862

Max Act: 3.9542. Min Act: -0.1700

Data Index: 699221 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 4.0862. Min Range: -4.0862

Max Act: 3.9613. Min Act: -0.1700

Data Index: 1000265 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 4.0862. Min Range: -4.0862

Max Act: 3.8993. Min Act: -0.1700

Data Index: 1303320 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 4.0862. Min Range: -4.0862

Max Act: 3.8756. Min Act: -0.1700

Data Index: 1310714 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 4.0862. Min Range: -4.0862

Max Act: 3.8468. Min Act: -0.1700

Data Index: 517882 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 4.0862. Min Range: -4.0862

Max Act: 3.8578. Min Act: -0.1700

Data Index: 13750 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 4.0862. Min Range: -4.0862

Max Act: 3.8285. Min Act: -0.1700

Data Index: 433130 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 4.0862. Min Range: -4.0862

Max Act: 3.8222. Min Act: -0.1700

Data Index: 28230 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 4.0862. Min Range: -4.0862

Max Act: 3.8411. Min Act: -0.1700

Data Index: 737559 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 4.0862. Min Range: -4.0862

Max Act: 3.8213. Min Act: -0.1700

Data Index: 939171 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 4.0862. Min Range: -4.0862

Max Act: 3.7992. Min Act: -0.1700

Data Index: 164481 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 4.0862. Min Range: -4.0862

Max Act: 3.8080. Min Act: -0.1700

Data Index: 639483 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 4.0862. Min Range: -4.0862

Max Act: 3.8089. Min Act: -0.1700

Data Index: 697525 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 4.0862. Min Range: -4.0862

Max Act: 3.8006. Min Act: -0.1700

Data Index: 382449 (C4 (Web Text))

Max Activating Token Index: 846

Text #18

Max Range: 4.0862. Min Range: -4.0862

Max Act: 3.8086. Min Act: -0.1700

Data Index: 464971 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 4.0862. Min Range: -4.0862

Max Act: 3.8072. Min Act: -0.1700

Data Index: 487652 (C4 (Web Text))

Max Activating Token Index: 708