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

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

Neuron 1670 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: 3.0518. Min Range: -3.0518

Max Act: 3.0518. Min Act: -0.1700

Data Index: 1046559 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 3.0518. Min Range: -3.0518

Max Act: 3.0349. Min Act: -0.1700

Data Index: 786280 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 3.0518. Min Range: -3.0518

Max Act: 3.0172. Min Act: -0.1700

Data Index: 1459940 (Python Code)

Max Activating Token Index: 882

Text #3

Max Range: 3.0518. Min Range: -3.0518

Max Act: 3.0278. Min Act: -0.1700

Data Index: 443634 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 3.0518. Min Range: -3.0518

Max Act: 3.0037. Min Act: -0.1700

Data Index: 113330 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 3.0518. Min Range: -3.0518

Max Act: 3.0069. Min Act: -0.1700

Data Index: 1605670 (Python Code)

Max Activating Token Index: 900

Text #6

Max Range: 3.0518. Min Range: -3.0518

Max Act: 2.9999. Min Act: -0.1700

Data Index: 627319 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 3.0518. Min Range: -3.0518

Max Act: 2.9998. Min Act: -0.1700

Data Index: 1502669 (Python Code)

Max Activating Token Index: 5

Text #8

Max Range: 3.0518. Min Range: -3.0518

Max Act: 2.9683. Min Act: -0.1700

Data Index: 1578950 (Python Code)

Max Activating Token Index: 166

Text #9

Max Range: 3.0518. Min Range: -3.0518

Max Act: 2.9766. Min Act: -0.1700

Data Index: 777026 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 3.0518. Min Range: -3.0518

Max Act: 2.9731. Min Act: -0.1700

Data Index: 1136375 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 3.0518. Min Range: -3.0518

Max Act: 2.9675. Min Act: -0.1700

Data Index: 9366 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 3.0518. Min Range: -3.0518

Max Act: 2.9556. Min Act: -0.1700

Data Index: 168859 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 3.0518. Min Range: -3.0518

Max Act: 2.9450. Min Act: -0.1700

Data Index: 1148299 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 3.0518. Min Range: -3.0518

Max Act: 2.9473. Min Act: -0.1700

Data Index: 1157171 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 3.0518. Min Range: -3.0518

Max Act: 2.9325. Min Act: -0.1694

Data Index: 605094 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 3.0518. Min Range: -3.0518

Max Act: 2.9245. Min Act: -0.1700

Data Index: 64025 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 3.0518. Min Range: -3.0518

Max Act: 2.9370. Min Act: -0.1700

Data Index: 678353 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 3.0518. Min Range: -3.0518

Max Act: 2.9400. Min Act: -0.1700

Data Index: 721909 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 3.0518. Min Range: -3.0518

Max Act: 2.8939. Min Act: -0.1700

Data Index: 1441346 (Python Code)

Max Activating Token Index: 573