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

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

Neuron 1897 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: 3.6688. Min Range: -3.6688

Max Act: 3.6688. Min Act: -0.1700

Data Index: 1010274 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 3.6688. Min Range: -3.6688

Max Act: 3.6531. Min Act: -0.1700

Data Index: 931548 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 3.6688. Min Range: -3.6688

Max Act: 3.5905. Min Act: -0.1700

Data Index: 1342652 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 3.6688. Min Range: -3.6688

Max Act: 3.5592. Min Act: -0.1700

Data Index: 173556 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 3.6688. Min Range: -3.6688

Max Act: 3.5279. Min Act: -0.1700

Data Index: 392272 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 3.6688. Min Range: -3.6688

Max Act: 3.5279. Min Act: -0.1700

Data Index: 387490 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 3.6688. Min Range: -3.6688

Max Act: 3.5122. Min Act: -0.1700

Data Index: 55013 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 3.6688. Min Range: -3.6688

Max Act: 3.4495. Min Act: -0.1700

Data Index: 540527 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 3.6688. Min Range: -3.6688

Max Act: 3.4495. Min Act: -0.1700

Data Index: 480943 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 3.6688. Min Range: -3.6688

Max Act: 3.4181. Min Act: -0.1700

Data Index: 473387 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 3.6688. Min Range: -3.6688

Max Act: 3.4338. Min Act: -0.1700

Data Index: 979521 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 3.6688. Min Range: -3.6688

Max Act: 3.3868. Min Act: -0.1700

Data Index: 998174 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 3.6688. Min Range: -3.6688

Max Act: 3.4181. Min Act: -0.1700

Data Index: 682523 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 3.6688. Min Range: -3.6688

Max Act: 3.3711. Min Act: -0.1700

Data Index: 668735 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 3.6688. Min Range: -3.6688

Max Act: 3.4181. Min Act: -0.1700

Data Index: 324013 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 3.6688. Min Range: -3.6688

Max Act: 3.3868. Min Act: -0.1700

Data Index: 697029 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 3.6688. Min Range: -3.6688

Max Act: 3.3868. Min Act: -0.1700

Data Index: 1107896 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 3.6688. Min Range: -3.6688

Max Act: 3.3554. Min Act: -0.1700

Data Index: 1300843 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 3.6688. Min Range: -3.6688

Max Act: 3.3554. Min Act: -0.1700

Data Index: 1277714 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 3.6688. Min Range: -3.6688

Max Act: 3.3868. Min Act: -0.1700

Data Index: 443734 (C4 (Web Text))

Max Activating Token Index: 172