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

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

Neuron 495 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: 4.0190. Min Range: -4.0190

Max Act: 4.0190. Min Act: -0.1699

Data Index: 456354 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 4.0190. Min Range: -4.0190

Max Act: 3.9579. Min Act: -0.1700

Data Index: 470332 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 4.0190. Min Range: -4.0190

Max Act: 3.9407. Min Act: -0.1699

Data Index: 298144 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 4.0190. Min Range: -4.0190

Max Act: 3.9463. Min Act: -0.1700

Data Index: 309635 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 4.0190. Min Range: -4.0190

Max Act: 3.9523. Min Act: -0.1700

Data Index: 1315332 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 4.0190. Min Range: -4.0190

Max Act: 3.9174. Min Act: -0.1700

Data Index: 695891 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 4.0190. Min Range: -4.0190

Max Act: 3.8658. Min Act: -0.1700

Data Index: 1312914 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 4.0190. Min Range: -4.0190

Max Act: 3.8713. Min Act: -0.1700

Data Index: 852128 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 4.0190. Min Range: -4.0190

Max Act: 3.8686. Min Act: -0.1700

Data Index: 177317 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 4.0190. Min Range: -4.0190

Max Act: 3.8390. Min Act: -0.1700

Data Index: 1123056 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 4.0190. Min Range: -4.0190

Max Act: 3.8516. Min Act: -0.1700

Data Index: 416717 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 4.0190. Min Range: -4.0190

Max Act: 3.8420. Min Act: -0.1700

Data Index: 1280752 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 4.0190. Min Range: -4.0190

Max Act: 3.8069. Min Act: -0.1688

Data Index: 155848 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 4.0190. Min Range: -4.0190

Max Act: 3.7995. Min Act: -0.1683

Data Index: 1175652 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 4.0190. Min Range: -4.0190

Max Act: 3.7735. Min Act: -0.1700

Data Index: 761454 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 4.0190. Min Range: -4.0190

Max Act: 3.7875. Min Act: -0.1700

Data Index: 619035 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 4.0190. Min Range: -4.0190

Max Act: 3.7759. Min Act: -0.1700

Data Index: 590016 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 4.0190. Min Range: -4.0190

Max Act: 3.7439. Min Act: -0.1700

Data Index: 59648 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 4.0190. Min Range: -4.0190

Max Act: 3.7471. Min Act: -0.1700

Data Index: 270858 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 4.0190. Min Range: -4.0190

Max Act: 3.7581. Min Act: -0.1700

Data Index: 23992 (C4 (Web Text))

Max Activating Token Index: 163