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

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

Neuron 50 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: 4.5174. Min Range: -4.5174

Max Act: 4.5174. Min Act: -0.1700

Data Index: 1247507 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.3494. Min Act: -0.1700

Data Index: 1261412 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.1856. Min Act: -0.1700

Data Index: 451141 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.1960. Min Act: -0.1700

Data Index: 1487886 (Python Code)

Max Activating Token Index: 888

Text #4

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.1729. Min Act: -0.1700

Data Index: 960057 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.1404. Min Act: -0.1700

Data Index: 1346652 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.0985. Min Act: -0.1700

Data Index: 652809 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.0856. Min Act: -0.1700

Data Index: 1438785 (Python Code)

Max Activating Token Index: 301

Text #8

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.0942. Min Act: -0.1700

Data Index: 1436059 (Python Code)

Max Activating Token Index: 169

Text #9

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.0811. Min Act: -0.1700

Data Index: 669942 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.0606. Min Act: -0.1700

Data Index: 357759 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.0573. Min Act: -0.1700

Data Index: 1329936 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.0801. Min Act: -0.1700

Data Index: 352420 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.0618. Min Act: -0.1700

Data Index: 894974 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.0496. Min Act: -0.1700

Data Index: 1617232 (Python Code)

Max Activating Token Index: 172

Text #15

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.0495. Min Act: -0.1700

Data Index: 686574 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.0422. Min Act: -0.1700

Data Index: 1304357 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.0103. Min Act: -0.1700

Data Index: 1618384 (Python Code)

Max Activating Token Index: 883

Text #18

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.0230. Min Act: -0.1700

Data Index: 1437655 (Python Code)

Max Activating Token Index: 997

Text #19

Max Range: 4.5174. Min Range: -4.5174

Max Act: 4.0382. Min Act: -0.1700

Data Index: 490038 (C4 (Web Text))

Max Activating Token Index: 508