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

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

Neuron 1658 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: 3.6415. Min Range: -3.6415

Max Act: 3.6415. Min Act: -0.1700

Data Index: 1655062 (Python Code)

Max Activating Token Index: 96

Text #1

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.5702. Min Act: -0.1700

Data Index: 1539164 (Python Code)

Max Activating Token Index: 75

Text #2

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.5522. Min Act: -0.1700

Data Index: 1507032 (Python Code)

Max Activating Token Index: 977

Text #3

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.4991. Min Act: -0.1700

Data Index: 1443113 (Python Code)

Max Activating Token Index: 1018

Text #4

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.4926. Min Act: -0.1700

Data Index: 937873 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.5205. Min Act: -0.1700

Data Index: 1612856 (Python Code)

Max Activating Token Index: 174

Text #6

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.5185. Min Act: -0.1700

Data Index: 875494 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.4742. Min Act: -0.1700

Data Index: 1456783 (Python Code)

Max Activating Token Index: 945

Text #8

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.5174. Min Act: -0.1700

Data Index: 1520434 (Python Code)

Max Activating Token Index: 42

Text #9

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.4787. Min Act: -0.1700

Data Index: 1623192 (Python Code)

Max Activating Token Index: 32

Text #10

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.4901. Min Act: -0.1700

Data Index: 1366517 (Python Code)

Max Activating Token Index: 986

Text #11

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.4553. Min Act: -0.1700

Data Index: 1393446 (Python Code)

Max Activating Token Index: 833

Text #12

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.4474. Min Act: -0.1700

Data Index: 1609761 (Python Code)

Max Activating Token Index: 68

Text #13

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.4628. Min Act: -0.1700

Data Index: 1581528 (Python Code)

Max Activating Token Index: 317

Text #14

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.4628. Min Act: -0.1700

Data Index: 300224 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.4148. Min Act: -0.1700

Data Index: 1390700 (Python Code)

Max Activating Token Index: 998

Text #16

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.4620. Min Act: -0.1700

Data Index: 1598948 (Python Code)

Max Activating Token Index: 747

Text #17

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.4716. Min Act: -0.1700

Data Index: 1449849 (Python Code)

Max Activating Token Index: 171

Text #18

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.4441. Min Act: -0.1700

Data Index: 1541729 (Python Code)

Max Activating Token Index: 614

Text #19

Max Range: 3.6415. Min Range: -3.6415

Max Act: 3.4781. Min Act: -0.1700

Data Index: 1412387 (Python Code)

Max Activating Token Index: 553