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

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

Neuron 412 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6366. Min Range: -3.6366

Max Act: 3.6366. Min Act: -0.1700

Data Index: 186226 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 3.6366. Min Range: -3.6366

Max Act: 3.6052. Min Act: -0.1700

Data Index: 610618 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 3.6366. Min Range: -3.6366

Max Act: 3.5739. Min Act: -0.1700

Data Index: 1341431 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 3.6366. Min Range: -3.6366

Max Act: 3.5739. Min Act: -0.1700

Data Index: 727084 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 3.6366. Min Range: -3.6366

Max Act: 3.5583. Min Act: -0.1700

Data Index: 155909 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 3.6366. Min Range: -3.6366

Max Act: 3.5583. Min Act: -0.1700

Data Index: 286505 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 3.6366. Min Range: -3.6366

Max Act: 3.5583. Min Act: -0.1700

Data Index: 708308 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 3.6366. Min Range: -3.6366

Max Act: 3.5269. Min Act: -0.1700

Data Index: 1128444 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 3.6366. Min Range: -3.6366

Max Act: 3.5269. Min Act: -0.1700

Data Index: 255566 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 3.6366. Min Range: -3.6366

Max Act: 3.5113. Min Act: -0.1700

Data Index: 1222062 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 3.6366. Min Range: -3.6366

Max Act: 3.5113. Min Act: -0.1700

Data Index: 577331 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 3.6366. Min Range: -3.6366

Max Act: 3.4956. Min Act: -0.1700

Data Index: 1345632 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 3.6366. Min Range: -3.6366

Max Act: 3.4956. Min Act: -0.1700

Data Index: 1085397 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 3.6366. Min Range: -3.6366

Max Act: 3.4643. Min Act: -0.1700

Data Index: 193340 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 3.6366. Min Range: -3.6366

Max Act: 3.4956. Min Act: -0.1700

Data Index: 673884 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 3.6366. Min Range: -3.6366

Max Act: 3.4799. Min Act: -0.1700

Data Index: 1201651 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 3.6366. Min Range: -3.6366

Max Act: 3.4329. Min Act: -0.1700

Data Index: 1220851 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 3.6366. Min Range: -3.6366

Max Act: 3.4486. Min Act: -0.1700

Data Index: 960811 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 3.6366. Min Range: -3.6366

Max Act: 3.4643. Min Act: -0.1700

Data Index: 367809 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 3.6366. Min Range: -3.6366

Max Act: 3.4329. Min Act: -0.1700

Data Index: 570263 (C4 (Web Text))

Max Activating Token Index: 601