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

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

Neuron 1958 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5033. Min Range: -3.5033

Max Act: 3.5033. Min Act: -0.1700

Data Index: 364948 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 3.5033. Min Range: -3.5033

Max Act: 3.4719. Min Act: -0.1700

Data Index: 1289040 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 3.5033. Min Range: -3.5033

Max Act: 3.4719. Min Act: -0.1700

Data Index: 851618 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 3.5033. Min Range: -3.5033

Max Act: 3.4876. Min Act: -0.1700

Data Index: 928989 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 3.5033. Min Range: -3.5033

Max Act: 3.4876. Min Act: -0.1700

Data Index: 1308070 (C4 (Web Text))

Max Activating Token Index: 561

Text #5

Max Range: 3.5033. Min Range: -3.5033

Max Act: 3.4876. Min Act: -0.1700

Data Index: 665831 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 3.5033. Min Range: -3.5033

Max Act: 3.4876. Min Act: -0.1700

Data Index: 718823 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 3.5033. Min Range: -3.5033

Max Act: 3.4562. Min Act: -0.1700

Data Index: 844868 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 3.5033. Min Range: -3.5033

Max Act: 3.4719. Min Act: -0.1700

Data Index: 301188 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 3.5033. Min Range: -3.5033

Max Act: 3.4719. Min Act: -0.1700

Data Index: 1091315 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 3.5033. Min Range: -3.5033

Max Act: 3.4719. Min Act: -0.1700

Data Index: 56393 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 3.5033. Min Range: -3.5033

Max Act: 3.4562. Min Act: -0.1700

Data Index: 20353 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 3.5033. Min Range: -3.5033

Max Act: 3.4562. Min Act: -0.1700

Data Index: 1171159 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 3.5033. Min Range: -3.5033

Max Act: 3.4406. Min Act: -0.1700

Data Index: 1055391 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 3.5033. Min Range: -3.5033

Max Act: 3.4249. Min Act: -0.1700

Data Index: 325682 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 3.5033. Min Range: -3.5033

Max Act: 3.4406. Min Act: -0.1700

Data Index: 275490 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 3.5033. Min Range: -3.5033

Max Act: 3.4406. Min Act: -0.1700

Data Index: 547048 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 3.5033. Min Range: -3.5033

Max Act: 3.4249. Min Act: -0.1700

Data Index: 914310 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 3.5033. Min Range: -3.5033

Max Act: 3.4249. Min Act: -0.1700

Data Index: 651534 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 3.5033. Min Range: -3.5033

Max Act: 3.4406. Min Act: -0.1700

Data Index: 628466 (C4 (Web Text))

Max Activating Token Index: 51