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

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

Neuron 1238 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: 3.4592. Min Range: -3.4592

Max Act: 3.4592. Min Act: -0.1700

Data Index: 365463 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 3.4592. Min Range: -3.4592

Max Act: 3.3337. Min Act: -0.1700

Data Index: 1246123 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 3.4592. Min Range: -3.4592

Max Act: 3.3337. Min Act: -0.1700

Data Index: 447654 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 3.4592. Min Range: -3.4592

Max Act: 3.2709. Min Act: -0.1700

Data Index: 423598 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 3.4592. Min Range: -3.4592

Max Act: 3.2395. Min Act: -0.1700

Data Index: 755015 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 3.4592. Min Range: -3.4592

Max Act: 3.2395. Min Act: -0.1700

Data Index: 404095 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 3.4592. Min Range: -3.4592

Max Act: 3.2238. Min Act: -0.1700

Data Index: 383065 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 3.4592. Min Range: -3.4592

Max Act: 3.2552. Min Act: -0.1700

Data Index: 925140 (C4 (Web Text))

Max Activating Token Index: 776

Text #8

Max Range: 3.4592. Min Range: -3.4592

Max Act: 3.2080. Min Act: -0.1700

Data Index: 418078 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 3.4592. Min Range: -3.4592

Max Act: 3.1923. Min Act: -0.1700

Data Index: 172735 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 3.4592. Min Range: -3.4592

Max Act: 3.2238. Min Act: -0.1700

Data Index: 487783 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 3.4592. Min Range: -3.4592

Max Act: 3.2080. Min Act: -0.1700

Data Index: 625481 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 3.4592. Min Range: -3.4592

Max Act: 3.1923. Min Act: -0.1700

Data Index: 1357134 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 3.4592. Min Range: -3.4592

Max Act: 3.1923. Min Act: -0.1700

Data Index: 236057 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 3.4592. Min Range: -3.4592

Max Act: 3.2080. Min Act: -0.1700

Data Index: 6341 (C4 (Web Text))

Max Activating Token Index: 465

Text #15

Max Range: 3.4592. Min Range: -3.4592

Max Act: 3.2080. Min Act: -0.1700

Data Index: 539855 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 3.4592. Min Range: -3.4592

Max Act: 3.1923. Min Act: -0.1700

Data Index: 165115 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 3.4592. Min Range: -3.4592

Max Act: 3.2238. Min Act: -0.1700

Data Index: 130422 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 3.4592. Min Range: -3.4592

Max Act: 3.2080. Min Act: -0.1700

Data Index: 590706 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 3.4592. Min Range: -3.4592

Max Act: 3.1766. Min Act: -0.1700

Data Index: 103539 (C4 (Web Text))

Max Activating Token Index: 120