Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1337 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.4043. Min Range: -3.4043

Max Act: 3.4043. Min Act: -0.1700

Data Index: 629341 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 3.4043. Min Range: -3.4043

Max Act: 3.2630. Min Act: -0.1700

Data Index: 352448 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 3.4043. Min Range: -3.4043

Max Act: 3.2316. Min Act: -0.1700

Data Index: 1025477 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 3.4043. Min Range: -3.4043

Max Act: 3.2630. Min Act: -0.1700

Data Index: 313495 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 3.4043. Min Range: -3.4043

Max Act: 3.2001. Min Act: -0.1700

Data Index: 409427 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 3.4043. Min Range: -3.4043

Max Act: 3.1686. Min Act: -0.1700

Data Index: 197395 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 3.4043. Min Range: -3.4043

Max Act: 3.2001. Min Act: -0.1700

Data Index: 1242371 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 3.4043. Min Range: -3.4043

Max Act: 3.1844. Min Act: -0.1700

Data Index: 1018064 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 3.4043. Min Range: -3.4043

Max Act: 3.1844. Min Act: -0.1700

Data Index: 265955 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 3.4043. Min Range: -3.4043

Max Act: 3.1529. Min Act: -0.1700

Data Index: 34534 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 3.4043. Min Range: -3.4043

Max Act: 3.1371. Min Act: -0.1700

Data Index: 612394 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 3.4043. Min Range: -3.4043

Max Act: 3.1529. Min Act: -0.1700

Data Index: 744997 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 3.4043. Min Range: -3.4043

Max Act: 3.1214. Min Act: -0.1700

Data Index: 306505 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 3.4043. Min Range: -3.4043

Max Act: 3.1214. Min Act: -0.1700

Data Index: 1032479 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 3.4043. Min Range: -3.4043

Max Act: 3.1056. Min Act: -0.1700

Data Index: 618458 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 3.4043. Min Range: -3.4043

Max Act: 3.1056. Min Act: -0.1700

Data Index: 338369 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 3.4043. Min Range: -3.4043

Max Act: 3.1214. Min Act: -0.1700

Data Index: 545695 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 3.4043. Min Range: -3.4043

Max Act: 3.0741. Min Act: -0.1700

Data Index: 1345884 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 3.4043. Min Range: -3.4043

Max Act: 3.1056. Min Act: -0.1700

Data Index: 807104 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 3.4043. Min Range: -3.4043

Max Act: 3.0899. Min Act: -0.1700

Data Index: 247819 (C4 (Web Text))

Max Activating Token Index: 487