Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 962 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.5703. Min Range: -3.5703

Max Act: 3.5703. Min Act: -0.1700

Data Index: 1280633 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 3.5703. Min Range: -3.5703

Max Act: 3.5381. Min Act: -0.1700

Data Index: 627002 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 3.5703. Min Range: -3.5703

Max Act: 3.4503. Min Act: -0.1700

Data Index: 197981 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 3.5703. Min Range: -3.5703

Max Act: 3.4016. Min Act: -0.1700

Data Index: 40020 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 3.5703. Min Range: -3.5703

Max Act: 3.4180. Min Act: -0.1700

Data Index: 1260223 (C4 (Web Text))

Max Activating Token Index: 412

Text #5

Max Range: 3.5703. Min Range: -3.5703

Max Act: 3.3557. Min Act: -0.1700

Data Index: 88289 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 3.5703. Min Range: -3.5703

Max Act: 3.3321. Min Act: -0.1700

Data Index: 919094 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 3.5703. Min Range: -3.5703

Max Act: 3.3238. Min Act: -0.1700

Data Index: 381681 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 3.5703. Min Range: -3.5703

Max Act: 3.2990. Min Act: -0.1700

Data Index: 72874 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 3.5703. Min Range: -3.5703

Max Act: 3.3298. Min Act: -0.1700

Data Index: 1281578 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 3.5703. Min Range: -3.5703

Max Act: 3.2984. Min Act: -0.1700

Data Index: 1313151 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 3.5703. Min Range: -3.5703

Max Act: 3.2678. Min Act: -0.1700

Data Index: 876088 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 3.5703. Min Range: -3.5703

Max Act: 3.2803. Min Act: -0.1700

Data Index: 1317331 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 3.5703. Min Range: -3.5703

Max Act: 3.2436. Min Act: -0.1700

Data Index: 1042175 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 3.5703. Min Range: -3.5703

Max Act: 3.2408. Min Act: -0.1700

Data Index: 220161 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 3.5703. Min Range: -3.5703

Max Act: 3.2458. Min Act: -0.1700

Data Index: 842547 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 3.5703. Min Range: -3.5703

Max Act: 3.2414. Min Act: -0.1700

Data Index: 942197 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 3.5703. Min Range: -3.5703

Max Act: 3.2320. Min Act: -0.1700

Data Index: 735537 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 3.5703. Min Range: -3.5703

Max Act: 3.1987. Min Act: -0.1700

Data Index: 590988 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 3.5703. Min Range: -3.5703

Max Act: 3.2316. Min Act: -0.1700

Data Index: 340737 (C4 (Web Text))

Max Activating Token Index: 184