Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1347 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.5060. Min Act: -0.1700

Data Index: 487706 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.4590. Min Act: -0.1700

Data Index: 627266 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.4276. Min Act: -0.1700

Data Index: 966982 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.3805. Min Act: -0.1700

Data Index: 283979 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.3805. Min Act: -0.1700

Data Index: 1330688 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.3962. Min Act: -0.1700

Data Index: 848238 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.4119. Min Act: -0.1700

Data Index: 1222292 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.3805. Min Act: -0.1700

Data Index: 190030 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.3492. Min Act: -0.1700

Data Index: 229892 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.4119. Min Act: -0.1700

Data Index: 1105578 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.3649. Min Act: -0.1700

Data Index: 39753 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.3962. Min Act: -0.1700

Data Index: 611767 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.3962. Min Act: -0.1700

Data Index: 567515 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.3492. Min Act: -0.1700

Data Index: 368501 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.3649. Min Act: -0.1700

Data Index: 322527 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.3649. Min Act: -0.1700

Data Index: 44092 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.3492. Min Act: -0.1700

Data Index: 396132 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.3021. Min Act: -0.1700

Data Index: 24038 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.3335. Min Act: -0.1700

Data Index: 818002 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 3.5060. Min Range: -3.5060

Max Act: 3.3492. Min Act: -0.1700

Data Index: 200125 (C4 (Web Text))

Max Activating Token Index: 381