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

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

Neuron 1247 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: 4.5711. Min Range: -4.5711

Max Act: 4.5711. Min Act: -0.1699

Data Index: 1312650 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 4.5711. Min Range: -4.5711

Max Act: 4.4954. Min Act: -0.1699

Data Index: 1115895 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 4.5711. Min Range: -4.5711

Max Act: 4.4416. Min Act: -0.1700

Data Index: 288959 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 4.5711. Min Range: -4.5711

Max Act: 4.3281. Min Act: -0.1699

Data Index: 129068 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 4.5711. Min Range: -4.5711

Max Act: 4.3341. Min Act: -0.1700

Data Index: 452490 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 4.5711. Min Range: -4.5711

Max Act: 4.3276. Min Act: -0.1699

Data Index: 282861 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 4.5711. Min Range: -4.5711

Max Act: 4.2966. Min Act: -0.1686

Data Index: 1022218 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 4.5711. Min Range: -4.5711

Max Act: 4.3281. Min Act: -0.1700

Data Index: 1174242 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 4.5711. Min Range: -4.5711

Max Act: 4.3061. Min Act: -0.1698

Data Index: 1191611 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 4.5711. Min Range: -4.5711

Max Act: 4.3044. Min Act: -0.1696

Data Index: 619867 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 4.5711. Min Range: -4.5711

Max Act: 4.2747. Min Act: -0.1698

Data Index: 124493 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 4.5711. Min Range: -4.5711

Max Act: 4.2740. Min Act: -0.1690

Data Index: 278816 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 4.5711. Min Range: -4.5711

Max Act: 4.2862. Min Act: -0.1700

Data Index: 1217607 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 4.5711. Min Range: -4.5711

Max Act: 4.2693. Min Act: -0.1699

Data Index: 196639 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 4.5711. Min Range: -4.5711

Max Act: 4.2843. Min Act: -0.1679

Data Index: 997959 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 4.5711. Min Range: -4.5711

Max Act: 4.2482. Min Act: -0.1698

Data Index: 230345 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 4.5711. Min Range: -4.5711

Max Act: 4.2235. Min Act: -0.1699

Data Index: 549689 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 4.5711. Min Range: -4.5711

Max Act: 4.2061. Min Act: -0.1697

Data Index: 749266 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 4.5711. Min Range: -4.5711

Max Act: 4.2126. Min Act: -0.1693

Data Index: 437788 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 4.5711. Min Range: -4.5711

Max Act: 4.2216. Min Act: -0.1698

Data Index: 820985 (C4 (Web Text))

Max Activating Token Index: 1023