Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 85 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.8982. Min Range: -5.8982

Max Act: 5.8982. Min Act: -0.1700

Data Index: 599407 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 5.8982. Min Range: -5.8982

Max Act: 5.7419. Min Act: -0.1700

Data Index: 624403 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 5.8982. Min Range: -5.8982

Max Act: 5.6169. Min Act: -0.1700

Data Index: 981873 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 5.8982. Min Range: -5.8982

Max Act: 5.6169. Min Act: -0.1700

Data Index: 359067 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 5.8982. Min Range: -5.8982

Max Act: 5.5544. Min Act: -0.1700

Data Index: 1145383 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 5.8982. Min Range: -5.8982

Max Act: 5.6482. Min Act: -0.1700

Data Index: 337411 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 5.8982. Min Range: -5.8982

Max Act: 5.6169. Min Act: -0.1700

Data Index: 376941 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 5.8982. Min Range: -5.8982

Max Act: 5.4919. Min Act: -0.1700

Data Index: 827561 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 5.8982. Min Range: -5.8982

Max Act: 5.5232. Min Act: -0.1700

Data Index: 409979 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 5.8982. Min Range: -5.8982

Max Act: 5.5232. Min Act: -0.1700

Data Index: 1068843 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 5.8982. Min Range: -5.8982

Max Act: 5.3982. Min Act: -0.1700

Data Index: 1319254 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 5.8982. Min Range: -5.8982

Max Act: 5.4294. Min Act: -0.1700

Data Index: 1259324 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 5.8982. Min Range: -5.8982

Max Act: 5.4607. Min Act: -0.1700

Data Index: 906272 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 5.8982. Min Range: -5.8982

Max Act: 5.4294. Min Act: -0.1700

Data Index: 537964 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 5.8982. Min Range: -5.8982

Max Act: 5.4919. Min Act: -0.1700

Data Index: 834501 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 5.8982. Min Range: -5.8982

Max Act: 5.4607. Min Act: -0.1700

Data Index: 173101 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 5.8982. Min Range: -5.8982

Max Act: 5.4294. Min Act: -0.1700

Data Index: 177888 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 5.8982. Min Range: -5.8982

Max Act: 5.5232. Min Act: -0.1700

Data Index: 448130 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 5.8982. Min Range: -5.8982

Max Act: 5.3982. Min Act: -0.1700

Data Index: 393975 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 5.8982. Min Range: -5.8982

Max Act: 5.4607. Min Act: -0.1700

Data Index: 339433 (C4 (Web Text))

Max Activating Token Index: 156