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

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

Neuron 125 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: 3.5111. Min Range: -3.5111

Max Act: 3.4922. Min Act: -0.1699

Data Index: 1546536 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 3.5111. Min Range: -3.5111

Max Act: 3.5111. Min Act: -0.1699

Data Index: 1459788 (Python Code)

Max Activating Token Index: 620

Text #2

Max Range: 3.5111. Min Range: -3.5111

Max Act: 3.4639. Min Act: -0.1700

Data Index: 1505056 (Python Code)

Max Activating Token Index: 34

Text #3

Max Range: 3.5111. Min Range: -3.5111

Max Act: 3.4632. Min Act: -0.1700

Data Index: 1428690 (Python Code)

Max Activating Token Index: 554

Text #4

Max Range: 3.5111. Min Range: -3.5111

Max Act: 3.4508. Min Act: -0.1700

Data Index: 1361116 (Python Code)

Max Activating Token Index: 322

Text #5

Max Range: 3.5111. Min Range: -3.5111

Max Act: 3.4317. Min Act: -0.1700

Data Index: 1401378 (Python Code)

Max Activating Token Index: 269

Text #6

Max Range: 3.5111. Min Range: -3.5111

Max Act: 3.4554. Min Act: -0.1700

Data Index: 1575132 (Python Code)

Max Activating Token Index: 143

Text #7

Max Range: 3.5111. Min Range: -3.5111

Max Act: 3.4542. Min Act: -0.1700

Data Index: 1380671 (Python Code)

Max Activating Token Index: 328

Text #8

Max Range: 3.5111. Min Range: -3.5111

Max Act: 3.4279. Min Act: -0.1700

Data Index: 1375799 (Python Code)

Max Activating Token Index: 307

Text #9

Max Range: 3.5111. Min Range: -3.5111

Max Act: 3.4221. Min Act: -0.1700

Data Index: 1461845 (Python Code)

Max Activating Token Index: 166

Text #10

Max Range: 3.5111. Min Range: -3.5111

Max Act: 3.3928. Min Act: -0.1700

Data Index: 1591730 (Python Code)

Max Activating Token Index: 186

Text #11

Max Range: 3.5111. Min Range: -3.5111

Max Act: 3.4140. Min Act: -0.1700

Data Index: 1552214 (Python Code)

Max Activating Token Index: 472

Text #12

Max Range: 3.5111. Min Range: -3.5111

Max Act: 3.4052. Min Act: -0.1700

Data Index: 1651424 (Python Code)

Max Activating Token Index: 319

Text #13

Max Range: 3.5111. Min Range: -3.5111

Max Act: 3.3952. Min Act: -0.1700

Data Index: 1338488 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 3.5111. Min Range: -3.5111

Max Act: 3.4087. Min Act: -0.1700

Data Index: 1453480 (Python Code)

Max Activating Token Index: 59

Text #15

Max Range: 3.5111. Min Range: -3.5111

Max Act: 3.3940. Min Act: -0.1700

Data Index: 1561750 (Python Code)

Max Activating Token Index: 40

Text #16

Max Range: 3.5111. Min Range: -3.5111

Max Act: 3.3850. Min Act: -0.1700

Data Index: 1619431 (Python Code)

Max Activating Token Index: 147

Text #17

Max Range: 3.5111. Min Range: -3.5111

Max Act: 3.3975. Min Act: -0.1700

Data Index: 1537220 (Python Code)

Max Activating Token Index: 442

Text #18

Max Range: 3.5111. Min Range: -3.5111

Max Act: 3.4087. Min Act: -0.1700

Data Index: 1424056 (Python Code)

Max Activating Token Index: 197

Text #19

Max Range: 3.5111. Min Range: -3.5111

Max Act: 3.3947. Min Act: -0.1700

Data Index: 444420 (C4 (Web Text))

Max Activating Token Index: 173