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

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

Neuron 1351 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: 3.2787. Min Range: -3.2787

Max Act: 3.2787. Min Act: -0.1700

Data Index: 507862 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.2042. Min Act: -0.1694

Data Index: 1281496 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.1794. Min Act: -0.1700

Data Index: 615046 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.1563. Min Act: -0.1699

Data Index: 1183147 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.1617. Min Act: -0.1698

Data Index: 1129018 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.1357. Min Act: -0.1700

Data Index: 759518 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.1352. Min Act: -0.1700

Data Index: 360511 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.1302. Min Act: -0.1700

Data Index: 708533 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.1061. Min Act: -0.1700

Data Index: 1275739 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.1200. Min Act: -0.1700

Data Index: 4733 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.0981. Min Act: -0.1700

Data Index: 1279507 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.1164. Min Act: -0.1700

Data Index: 475494 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.0974. Min Act: -0.1700

Data Index: 578726 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.0774. Min Act: -0.1700

Data Index: 1125006 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.0545. Min Act: -0.1700

Data Index: 1140122 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.0597. Min Act: -0.1700

Data Index: 871957 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.0480. Min Act: -0.1700

Data Index: 490189 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.0540. Min Act: -0.1700

Data Index: 189110 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.0373. Min Act: -0.1688

Data Index: 239934 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 3.2787. Min Range: -3.2787

Max Act: 3.0310. Min Act: -0.1699

Data Index: 858277 (C4 (Web Text))

Max Activating Token Index: 565