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

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

Neuron 863 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: 4.2784. Min Range: -4.2784

Max Act: 4.2784. Min Act: -0.1700

Data Index: 394027 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 4.2784. Min Range: -4.2784

Max Act: 4.2178. Min Act: -0.1700

Data Index: 57496 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 4.2784. Min Range: -4.2784

Max Act: 4.2399. Min Act: -0.1700

Data Index: 511690 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 4.2784. Min Range: -4.2784

Max Act: 4.1349. Min Act: -0.1700

Data Index: 190821 (C4 (Web Text))

Max Activating Token Index: 413

Text #4

Max Range: 4.2784. Min Range: -4.2784

Max Act: 4.0993. Min Act: -0.1700

Data Index: 1492553 (Python Code)

Max Activating Token Index: 623

Text #5

Max Range: 4.2784. Min Range: -4.2784

Max Act: 4.1146. Min Act: -0.1700

Data Index: 1220497 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 4.2784. Min Range: -4.2784

Max Act: 4.0924. Min Act: -0.1700

Data Index: 1047369 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 4.2784. Min Range: -4.2784

Max Act: 4.0917. Min Act: -0.1700

Data Index: 29054 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 4.2784. Min Range: -4.2784

Max Act: 4.0630. Min Act: -0.1700

Data Index: 1623614 (Python Code)

Max Activating Token Index: 918

Text #9

Max Range: 4.2784. Min Range: -4.2784

Max Act: 4.0975. Min Act: -0.1700

Data Index: 736899 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 4.2784. Min Range: -4.2784

Max Act: 4.0362. Min Act: -0.1700

Data Index: 516348 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 4.2784. Min Range: -4.2784

Max Act: 4.0464. Min Act: -0.1700

Data Index: 164670 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 4.2784. Min Range: -4.2784

Max Act: 4.0472. Min Act: -0.1700

Data Index: 1060431 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 4.2784. Min Range: -4.2784

Max Act: 4.0314. Min Act: -0.1700

Data Index: 332049 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 4.2784. Min Range: -4.2784

Max Act: 4.0054. Min Act: -0.1700

Data Index: 667871 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 4.2784. Min Range: -4.2784

Max Act: 4.0335. Min Act: -0.1700

Data Index: 688332 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 4.2784. Min Range: -4.2784

Max Act: 4.0196. Min Act: -0.1700

Data Index: 591820 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 4.2784. Min Range: -4.2784

Max Act: 3.9797. Min Act: -0.1700

Data Index: 736237 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 4.2784. Min Range: -4.2784

Max Act: 4.0264. Min Act: -0.1700

Data Index: 409930 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 4.2784. Min Range: -4.2784

Max Act: 4.0174. Min Act: -0.1700

Data Index: 306295 (C4 (Web Text))

Max Activating Token Index: 22