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

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

Neuron 1256 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: 3.2856. Min Range: -3.2856

Max Act: 3.2856. Min Act: -0.1700

Data Index: 416936 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.1825. Min Act: -0.1700

Data Index: 500574 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.0783. Min Act: -0.1700

Data Index: 1044509 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.0735. Min Act: -0.1700

Data Index: 620421 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.0571. Min Act: -0.1700

Data Index: 1447109 (Python Code)

Max Activating Token Index: 996

Text #5

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.0743. Min Act: -0.1700

Data Index: 1469406 (Python Code)

Max Activating Token Index: 737

Text #6

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.0534. Min Act: -0.1700

Data Index: 1476576 (Python Code)

Max Activating Token Index: 248

Text #7

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.0452. Min Act: -0.1700

Data Index: 1443674 (Python Code)

Max Activating Token Index: 362

Text #8

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.0216. Min Act: -0.1700

Data Index: 1447054 (Python Code)

Max Activating Token Index: 999

Text #9

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.0075. Min Act: -0.1700

Data Index: 1486049 (Python Code)

Max Activating Token Index: 893

Text #10

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.0185. Min Act: -0.1700

Data Index: 1135412 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.0176. Min Act: -0.1700

Data Index: 1620261 (Python Code)

Max Activating Token Index: 599

Text #12

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.0019. Min Act: -0.1700

Data Index: 1468203 (Python Code)

Max Activating Token Index: 356

Text #13

Max Range: 3.2856. Min Range: -3.2856

Max Act: 2.9866. Min Act: -0.1700

Data Index: 1104776 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 3.2856. Min Range: -3.2856

Max Act: 2.9975. Min Act: -0.1700

Data Index: 1193141 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 3.2856. Min Range: -3.2856

Max Act: 2.9851. Min Act: -0.1700

Data Index: 210942 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 3.2856. Min Range: -3.2856

Max Act: 2.9942. Min Act: -0.1700

Data Index: 1568162 (Python Code)

Max Activating Token Index: 979

Text #17

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.0202. Min Act: -0.1700

Data Index: 1637408 (Python Code)

Max Activating Token Index: 969

Text #18

Max Range: 3.2856. Min Range: -3.2856

Max Act: 3.0271. Min Act: -0.1700

Data Index: 46659 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 3.2856. Min Range: -3.2856

Max Act: 2.9758. Min Act: -0.1700

Data Index: 1102244 (C4 (Web Text))

Max Activating Token Index: 881