Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1661 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 4.0341. Min Range: -4.0341

Max Act: 4.0341. Min Act: -0.1700

Data Index: 905680 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 4.0341. Min Range: -4.0341

Max Act: 3.7840. Min Act: -0.1700

Data Index: 207630 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 4.0341. Min Range: -4.0341

Max Act: 3.7840. Min Act: -0.1700

Data Index: 1161533 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 4.0341. Min Range: -4.0341

Max Act: 3.7214. Min Act: -0.1700

Data Index: 310216 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 4.0341. Min Range: -4.0341

Max Act: 3.7214. Min Act: -0.1700

Data Index: 293320 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 4.0341. Min Range: -4.0341

Max Act: 3.6901. Min Act: -0.1700

Data Index: 922432 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 4.0341. Min Range: -4.0341

Max Act: 3.7527. Min Act: -0.1699

Data Index: 940267 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 4.0341. Min Range: -4.0341

Max Act: 3.5649. Min Act: -0.1700

Data Index: 956786 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 4.0341. Min Range: -4.0341

Max Act: 3.5649. Min Act: -0.1700

Data Index: 112098 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 4.0341. Min Range: -4.0341

Max Act: 3.5649. Min Act: -0.1700

Data Index: 72377 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 4.0341. Min Range: -4.0341

Max Act: 3.5962. Min Act: -0.1700

Data Index: 976538 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 4.0341. Min Range: -4.0341

Max Act: 3.6275. Min Act: -0.1699

Data Index: 588828 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 4.0341. Min Range: -4.0341

Max Act: 3.5962. Min Act: -0.1700

Data Index: 1252028 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 4.0341. Min Range: -4.0341

Max Act: 3.5962. Min Act: -0.1700

Data Index: 566646 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 4.0341. Min Range: -4.0341

Max Act: 3.6275. Min Act: -0.1700

Data Index: 1359593 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 4.0341. Min Range: -4.0341

Max Act: 3.5962. Min Act: -0.1700

Data Index: 339292 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 4.0341. Min Range: -4.0341

Max Act: 3.6901. Min Act: -0.1700

Data Index: 669971 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 4.0341. Min Range: -4.0341

Max Act: 3.6275. Min Act: -0.1700

Data Index: 575854 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 4.0341. Min Range: -4.0341

Max Act: 3.5962. Min Act: -0.1700

Data Index: 432696 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 4.0341. Min Range: -4.0341

Max Act: 3.5962. Min Act: -0.1700

Data Index: 690958 (C4 (Web Text))

Max Activating Token Index: 168