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

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

Neuron 1176 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: 4.4624. Min Range: -4.4624

Max Act: 4.4624. Min Act: -0.1700

Data Index: 598603 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.2505. Min Act: -0.1700

Data Index: 1622560 (Python Code)

Max Activating Token Index: 158

Text #2

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.2208. Min Act: -0.1700

Data Index: 1017930 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.1846. Min Act: -0.1700

Data Index: 580699 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.1555. Min Act: -0.1700

Data Index: 362098 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.1268. Min Act: -0.1700

Data Index: 1619940 (Python Code)

Max Activating Token Index: 385

Text #6

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.0912. Min Act: -0.1700

Data Index: 779285 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.1217. Min Act: -0.1700

Data Index: 1482578 (Python Code)

Max Activating Token Index: 822

Text #8

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.1064. Min Act: -0.1700

Data Index: 62563 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.0812. Min Act: -0.1700

Data Index: 1204553 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.0672. Min Act: -0.1697

Data Index: 1127737 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.0393. Min Act: -0.1700

Data Index: 925865 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.0334. Min Act: -0.1700

Data Index: 1049593 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.0421. Min Act: -0.1700

Data Index: 858010 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 4.4624. Min Range: -4.4624

Max Act: 3.9949. Min Act: -0.1700

Data Index: 1559539 (Python Code)

Max Activating Token Index: 537

Text #15

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.0027. Min Act: -0.1700

Data Index: 1427260 (Python Code)

Max Activating Token Index: 675

Text #16

Max Range: 4.4624. Min Range: -4.4624

Max Act: 3.9864. Min Act: -0.1700

Data Index: 1210931 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.0169. Min Act: -0.1700

Data Index: 665429 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 4.4624. Min Range: -4.4624

Max Act: 3.9905. Min Act: -0.1699

Data Index: 470400 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 4.4624. Min Range: -4.4624

Max Act: 4.0256. Min Act: -0.1700

Data Index: 541363 (C4 (Web Text))

Max Activating Token Index: 1008