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

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

Neuron 375 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: 3.5764. Min Range: -3.5764

Max Act: 3.5764. Min Act: -0.1700

Data Index: 558419 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 3.5764. Min Range: -3.5764

Max Act: 3.5238. Min Act: -0.1700

Data Index: 1343079 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 3.5764. Min Range: -3.5764

Max Act: 3.4380. Min Act: -0.1700

Data Index: 1345355 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 3.5764. Min Range: -3.5764

Max Act: 3.4424. Min Act: -0.1700

Data Index: 279789 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 3.5764. Min Range: -3.5764

Max Act: 3.3964. Min Act: -0.1700

Data Index: 364800 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 3.5764. Min Range: -3.5764

Max Act: 3.4233. Min Act: -0.1700

Data Index: 789477 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 3.5764. Min Range: -3.5764

Max Act: 3.4307. Min Act: -0.1700

Data Index: 1294751 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 3.5764. Min Range: -3.5764

Max Act: 3.4008. Min Act: -0.1700

Data Index: 287826 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 3.5764. Min Range: -3.5764

Max Act: 3.4109. Min Act: -0.1700

Data Index: 878083 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 3.5764. Min Range: -3.5764

Max Act: 3.3973. Min Act: -0.1700

Data Index: 696064 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 3.5764. Min Range: -3.5764

Max Act: 3.3903. Min Act: -0.1700

Data Index: 1073107 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 3.5764. Min Range: -3.5764

Max Act: 3.3244. Min Act: -0.1700

Data Index: 926398 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 3.5764. Min Range: -3.5764

Max Act: 3.3683. Min Act: -0.1700

Data Index: 49557 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 3.5764. Min Range: -3.5764

Max Act: 3.3675. Min Act: -0.1700

Data Index: 476883 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 3.5764. Min Range: -3.5764

Max Act: 3.3316. Min Act: -0.1700

Data Index: 53438 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 3.5764. Min Range: -3.5764

Max Act: 3.3739. Min Act: -0.1700

Data Index: 378359 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 3.5764. Min Range: -3.5764

Max Act: 3.3287. Min Act: -0.1700

Data Index: 538927 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 3.5764. Min Range: -3.5764

Max Act: 3.3634. Min Act: -0.1700

Data Index: 1037337 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 3.5764. Min Range: -3.5764

Max Act: 3.3194. Min Act: -0.1700

Data Index: 418007 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 3.5764. Min Range: -3.5764

Max Act: 3.3643. Min Act: -0.1700

Data Index: 1092942 (C4 (Web Text))

Max Activating Token Index: 585