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

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

Neuron 588 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: 7.6445. Min Range: -7.6445

Max Act: 7.6445. Min Act: -0.1700

Data Index: 271948 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 7.6445. Min Range: -7.6445

Max Act: 7.5195. Min Act: -0.1700

Data Index: 1147535 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 7.6445. Min Range: -7.6445

Max Act: 7.5820. Min Act: -0.1700

Data Index: 1462450 (Python Code)

Max Activating Token Index: 483

Text #3

Max Range: 7.6445. Min Range: -7.6445

Max Act: 7.3320. Min Act: -0.1700

Data Index: 1386087 (Python Code)

Max Activating Token Index: 929

Text #4

Max Range: 7.6445. Min Range: -7.6445

Max Act: 7.2695. Min Act: -0.1700

Data Index: 684972 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 7.6445. Min Range: -7.6445

Max Act: 7.3320. Min Act: -0.1700

Data Index: 1486849 (Python Code)

Max Activating Token Index: 353

Text #6

Max Range: 7.6445. Min Range: -7.6445

Max Act: 7.3320. Min Act: -0.1700

Data Index: 1045795 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 7.6445. Min Range: -7.6445

Max Act: 7.2695. Min Act: -0.1700

Data Index: 1271387 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 7.6445. Min Range: -7.6445

Max Act: 7.2695. Min Act: -0.1700

Data Index: 1446235 (Python Code)

Max Activating Token Index: 1008

Text #9

Max Range: 7.6445. Min Range: -7.6445

Max Act: 7.2695. Min Act: -0.1700

Data Index: 1139002 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 7.6445. Min Range: -7.6445

Max Act: 7.2070. Min Act: -0.1700

Data Index: 581470 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 7.6445. Min Range: -7.6445

Max Act: 7.2070. Min Act: -0.1700

Data Index: 224022 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 7.6445. Min Range: -7.6445

Max Act: 7.3320. Min Act: -0.1700

Data Index: 289849 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 7.6445. Min Range: -7.6445

Max Act: 7.2070. Min Act: -0.1700

Data Index: 948315 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 7.6445. Min Range: -7.6445

Max Act: 7.2070. Min Act: -0.1700

Data Index: 636741 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 7.6445. Min Range: -7.6445

Max Act: 7.1445. Min Act: -0.1700

Data Index: 1487781 (Python Code)

Max Activating Token Index: 630

Text #16

Max Range: 7.6445. Min Range: -7.6445

Max Act: 7.0195. Min Act: -0.1700

Data Index: 1250396 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 7.6445. Min Range: -7.6445

Max Act: 7.0820. Min Act: -0.1700

Data Index: 730657 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 7.6445. Min Range: -7.6445

Max Act: 7.0820. Min Act: -0.1700

Data Index: 1477798 (Python Code)

Max Activating Token Index: 939

Text #19

Max Range: 7.6445. Min Range: -7.6445

Max Act: 7.0195. Min Act: -0.1700

Data Index: 110206 (C4 (Web Text))

Max Activating Token Index: 971