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

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

Neuron 710 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: 3.9120. Min Range: -3.9120

Max Act: 3.9120. Min Act: -0.1700

Data Index: 856837 (C4 (Web Text))

Max Activating Token Index: 685

Text #1

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.8056. Min Act: -0.1700

Data Index: 18566 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.7272. Min Act: -0.1700

Data Index: 952558 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.6838. Min Act: -0.1700

Data Index: 808849 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.6528. Min Act: -0.1700

Data Index: 56004 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.6378. Min Act: -0.1700

Data Index: 1552076 (Python Code)

Max Activating Token Index: 910

Text #6

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.6672. Min Act: -0.1700

Data Index: 555895 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.6536. Min Act: -0.1700

Data Index: 866756 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.6458. Min Act: -0.1700

Data Index: 578442 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.6527. Min Act: -0.1700

Data Index: 1236850 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.6243. Min Act: -0.1700

Data Index: 375181 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.6168. Min Act: -0.1700

Data Index: 961076 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.6191. Min Act: -0.1700

Data Index: 662819 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.6345. Min Act: -0.1700

Data Index: 253640 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.6109. Min Act: -0.1700

Data Index: 387454 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.6522. Min Act: -0.1700

Data Index: 264783 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.6038. Min Act: -0.1700

Data Index: 1230669 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.5995. Min Act: -0.1700

Data Index: 944686 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.6140. Min Act: -0.1700

Data Index: 1204981 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 3.9120. Min Range: -3.9120

Max Act: 3.6058. Min Act: -0.1700

Data Index: 695522 (C4 (Web Text))

Max Activating Token Index: 896