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

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

Neuron 730 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: 3.3566. Min Range: -3.3566

Max Act: 3.3566. Min Act: -0.1700

Data Index: 592942 (C4 (Web Text))

Max Activating Token Index: 597

Text #1

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.3409. Min Act: -0.1700

Data Index: 766532 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.3252. Min Act: -0.1700

Data Index: 518727 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.3409. Min Act: -0.1700

Data Index: 222597 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.2938. Min Act: -0.1700

Data Index: 823919 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.3095. Min Act: -0.1700

Data Index: 1226144 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.2938. Min Act: -0.1700

Data Index: 506662 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.2938. Min Act: -0.1700

Data Index: 953322 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.2938. Min Act: -0.1700

Data Index: 303527 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.2781. Min Act: -0.1700

Data Index: 273819 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.2781. Min Act: -0.1700

Data Index: 534945 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.2466. Min Act: -0.1700

Data Index: 641252 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.2623. Min Act: -0.1700

Data Index: 70747 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.2623. Min Act: -0.1700

Data Index: 559343 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.2309. Min Act: -0.1700

Data Index: 1022743 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.2466. Min Act: -0.1700

Data Index: 340949 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.2466. Min Act: -0.1700

Data Index: 1160033 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.2466. Min Act: -0.1700

Data Index: 466423 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.2152. Min Act: -0.1700

Data Index: 411596 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.2152. Min Act: -0.1700

Data Index: 291324 (C4 (Web Text))

Max Activating Token Index: 413