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

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

Neuron 563 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: 3.7938. Min Range: -3.7938

Max Act: 3.7938. Min Act: -0.1531

Data Index: 464402 (C4 (Web Text))

Max Activating Token Index: 931

Text #1

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.7138. Min Act: -0.1699

Data Index: 299423 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.7227. Min Act: -0.1531

Data Index: 385831 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.6918. Min Act: -0.1699

Data Index: 1304543 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.6583. Min Act: -0.1700

Data Index: 736163 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.6313. Min Act: -0.1699

Data Index: 1276927 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.5851. Min Act: -0.1531

Data Index: 1107948 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.6110. Min Act: -0.1695

Data Index: 202147 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.5768. Min Act: -0.1698

Data Index: 993473 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.5502. Min Act: -0.1668

Data Index: 407139 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.5454. Min Act: -0.1699

Data Index: 1028538 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.5482. Min Act: -0.1531

Data Index: 219876 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.5572. Min Act: -0.1678

Data Index: 567155 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.5272. Min Act: -0.1543

Data Index: 1366672 (Python Code)

Max Activating Token Index: 659

Text #14

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.5243. Min Act: -0.1699

Data Index: 348851 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.5140. Min Act: -0.1531

Data Index: 695317 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.5318. Min Act: -0.1531

Data Index: 701059 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.5267. Min Act: -0.1700

Data Index: 1524363 (Python Code)

Max Activating Token Index: 385

Text #18

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.5064. Min Act: -0.1694

Data Index: 702336 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 3.7938. Min Range: -3.7938

Max Act: 3.5013. Min Act: -0.1646

Data Index: 65725 (C4 (Web Text))

Max Activating Token Index: 348