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

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

Neuron 2003 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: 3.1741. Min Range: -3.1741

Max Act: 3.1741. Min Act: -0.1700

Data Index: 1347754 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 3.1741. Min Range: -3.1741

Max Act: 2.9856. Min Act: -0.1700

Data Index: 276946 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 3.1741. Min Range: -3.1741

Max Act: 2.9672. Min Act: -0.1700

Data Index: 1249800 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 3.1741. Min Range: -3.1741

Max Act: 2.9711. Min Act: -0.1700

Data Index: 904255 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 3.1741. Min Range: -3.1741

Max Act: 2.9545. Min Act: -0.1700

Data Index: 683643 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 3.1741. Min Range: -3.1741

Max Act: 2.9277. Min Act: -0.1700

Data Index: 780595 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 3.1741. Min Range: -3.1741

Max Act: 2.9468. Min Act: -0.1700

Data Index: 365172 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 3.1741. Min Range: -3.1741

Max Act: 2.9291. Min Act: -0.1700

Data Index: 305082 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 3.1741. Min Range: -3.1741

Max Act: 2.9111. Min Act: -0.1700

Data Index: 380061 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 3.1741. Min Range: -3.1741

Max Act: 2.9140. Min Act: -0.1700

Data Index: 20565 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 3.1741. Min Range: -3.1741

Max Act: 2.9253. Min Act: -0.1700

Data Index: 339701 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 3.1741. Min Range: -3.1741

Max Act: 2.9348. Min Act: -0.1700

Data Index: 975105 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 3.1741. Min Range: -3.1741

Max Act: 2.8627. Min Act: -0.1700

Data Index: 512981 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 3.1741. Min Range: -3.1741

Max Act: 2.8900. Min Act: -0.1700

Data Index: 1290026 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 3.1741. Min Range: -3.1741

Max Act: 2.8894. Min Act: -0.1700

Data Index: 99614 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 3.1741. Min Range: -3.1741

Max Act: 2.9153. Min Act: -0.1700

Data Index: 1170274 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 3.1741. Min Range: -3.1741

Max Act: 2.8768. Min Act: -0.1700

Data Index: 942381 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 3.1741. Min Range: -3.1741

Max Act: 2.8751. Min Act: -0.1700

Data Index: 512416 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 3.1741. Min Range: -3.1741

Max Act: 2.8620. Min Act: -0.1700

Data Index: 959835 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 3.1741. Min Range: -3.1741

Max Act: 2.8770. Min Act: -0.1700

Data Index: 513166 (C4 (Web Text))

Max Activating Token Index: 578