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

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

Neuron 690 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: 2.3895. Min Range: -2.3895

Max Act: 2.3895. Min Act: -0.1700

Data Index: 117026 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 2.3895. Min Range: -2.3895

Max Act: 2.3828. Min Act: -0.1700

Data Index: 1647446 (Python Code)

Max Activating Token Index: 897

Text #2

Max Range: 2.3895. Min Range: -2.3895

Max Act: 2.3439. Min Act: -0.1700

Data Index: 664844 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 2.3895. Min Range: -2.3895

Max Act: 2.3545. Min Act: -0.1700

Data Index: 1475112 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 2.3895. Min Range: -2.3895

Max Act: 2.3314. Min Act: -0.1700

Data Index: 1622642 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 2.3895. Min Range: -2.3895

Max Act: 2.3366. Min Act: -0.1700

Data Index: 149325 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 2.3895. Min Range: -2.3895

Max Act: 2.3358. Min Act: -0.1700

Data Index: 1359649 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 2.3895. Min Range: -2.3895

Max Act: 2.3144. Min Act: -0.1700

Data Index: 583301 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 2.3895. Min Range: -2.3895

Max Act: 2.3194. Min Act: -0.1700

Data Index: 1522441 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 2.3895. Min Range: -2.3895

Max Act: 2.3011. Min Act: -0.1700

Data Index: 613170 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 2.3895. Min Range: -2.3895

Max Act: 2.3068. Min Act: -0.1700

Data Index: 690932 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 2.3895. Min Range: -2.3895

Max Act: 2.2848. Min Act: -0.1700

Data Index: 736820 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 2.3895. Min Range: -2.3895

Max Act: 2.2867. Min Act: -0.1700

Data Index: 1192341 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 2.3895. Min Range: -2.3895

Max Act: 2.2696. Min Act: -0.1700

Data Index: 885492 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 2.3895. Min Range: -2.3895

Max Act: 2.2660. Min Act: -0.1700

Data Index: 223305 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 2.3895. Min Range: -2.3895

Max Act: 2.2665. Min Act: -0.1700

Data Index: 46331 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 2.3895. Min Range: -2.3895

Max Act: 2.2537. Min Act: -0.1700

Data Index: 63509 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 2.3895. Min Range: -2.3895

Max Act: 2.2669. Min Act: -0.1700

Data Index: 572728 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 2.3895. Min Range: -2.3895

Max Act: 2.2572. Min Act: -0.1700

Data Index: 1606293 (Python Code)

Max Activating Token Index: 189

Text #19

Max Range: 2.3895. Min Range: -2.3895

Max Act: 2.2371. Min Act: -0.1700

Data Index: 1518164 (Python Code)

Max Activating Token Index: 952