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

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

Neuron 737 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: 3.2862. Min Range: -3.2862

Max Act: 3.2862. Min Act: -0.1700

Data Index: 624612 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 3.2862. Min Range: -3.2862

Max Act: 3.2431. Min Act: -0.1700

Data Index: 748550 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 3.2862. Min Range: -3.2862

Max Act: 3.2655. Min Act: -0.1700

Data Index: 92708 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 3.2862. Min Range: -3.2862

Max Act: 3.2343. Min Act: -0.1700

Data Index: 1168584 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 3.2862. Min Range: -3.2862

Max Act: 3.2209. Min Act: -0.1700

Data Index: 502953 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 3.2862. Min Range: -3.2862

Max Act: 3.1790. Min Act: -0.1700

Data Index: 1185873 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 3.2862. Min Range: -3.2862

Max Act: 3.1980. Min Act: -0.1700

Data Index: 843449 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 3.2862. Min Range: -3.2862

Max Act: 3.1730. Min Act: -0.1700

Data Index: 790990 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 3.2862. Min Range: -3.2862

Max Act: 3.1682. Min Act: -0.1700

Data Index: 922544 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 3.2862. Min Range: -3.2862

Max Act: 3.1611. Min Act: -0.1700

Data Index: 400958 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 3.2862. Min Range: -3.2862

Max Act: 3.1794. Min Act: -0.1700

Data Index: 1089426 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 3.2862. Min Range: -3.2862

Max Act: 3.1689. Min Act: -0.1700

Data Index: 59579 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 3.2862. Min Range: -3.2862

Max Act: 3.1330. Min Act: -0.1700

Data Index: 708825 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 3.2862. Min Range: -3.2862

Max Act: 3.1375. Min Act: -0.1700

Data Index: 233275 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 3.2862. Min Range: -3.2862

Max Act: 3.1721. Min Act: -0.1700

Data Index: 398820 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 3.2862. Min Range: -3.2862

Max Act: 3.1598. Min Act: -0.1700

Data Index: 768428 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 3.2862. Min Range: -3.2862

Max Act: 3.1679. Min Act: -0.1700

Data Index: 1292998 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 3.2862. Min Range: -3.2862

Max Act: 3.1440. Min Act: -0.1700

Data Index: 972790 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 3.2862. Min Range: -3.2862

Max Act: 3.1616. Min Act: -0.1700

Data Index: 1207776 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 3.2862. Min Range: -3.2862

Max Act: 3.1565. Min Act: -0.1700

Data Index: 1062752 (C4 (Web Text))

Max Activating Token Index: 492