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

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

Neuron 2022 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: 4.9939. Min Range: -4.9939

Max Act: 4.9939. Min Act: -0.1639

Data Index: 102958 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 4.9939. Min Range: -4.9939

Max Act: 4.9615. Min Act: -0.1700

Data Index: 144497 (C4 (Web Text))

Max Activating Token Index: 705

Text #2

Max Range: 4.9939. Min Range: -4.9939

Max Act: 4.9727. Min Act: -0.1700

Data Index: 1232379 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 4.9939. Min Range: -4.9939

Max Act: 4.9635. Min Act: -0.1697

Data Index: 1214725 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 4.9939. Min Range: -4.9939

Max Act: 4.8864. Min Act: -0.1697

Data Index: 474951 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 4.9939. Min Range: -4.9939

Max Act: 4.8432. Min Act: -0.1639

Data Index: 1181233 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 4.9939. Min Range: -4.9939

Max Act: 4.8488. Min Act: -0.1700

Data Index: 424862 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 4.9939. Min Range: -4.9939

Max Act: 4.8202. Min Act: -0.1639

Data Index: 880925 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 4.9939. Min Range: -4.9939

Max Act: 4.7719. Min Act: -0.1700

Data Index: 857743 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 4.9939. Min Range: -4.9939

Max Act: 4.7589. Min Act: -0.1639

Data Index: 863829 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 4.9939. Min Range: -4.9939

Max Act: 4.7352. Min Act: -0.1700

Data Index: 669901 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 4.9939. Min Range: -4.9939

Max Act: 4.7449. Min Act: -0.1697

Data Index: 743793 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 4.9939. Min Range: -4.9939

Max Act: 4.7569. Min Act: -0.1639

Data Index: 969673 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 4.9939. Min Range: -4.9939

Max Act: 4.7419. Min Act: -0.1700

Data Index: 150161 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 4.9939. Min Range: -4.9939

Max Act: 4.7192. Min Act: -0.1700

Data Index: 732563 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 4.9939. Min Range: -4.9939

Max Act: 4.7190. Min Act: -0.1676

Data Index: 302591 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 4.9939. Min Range: -4.9939

Max Act: 4.6971. Min Act: -0.1692

Data Index: 1185085 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 4.9939. Min Range: -4.9939

Max Act: 4.6808. Min Act: -0.1700

Data Index: 1211400 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 4.9939. Min Range: -4.9939

Max Act: 4.7076. Min Act: -0.1700

Data Index: 255725 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 4.9939. Min Range: -4.9939

Max Act: 4.7161. Min Act: -0.1699

Data Index: 268394 (C4 (Web Text))

Max Activating Token Index: 649