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

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

Neuron 886 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: 4.5327. Min Range: -4.5327

Max Act: 4.5327. Min Act: -0.1698

Data Index: 1076247 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 4.5327. Min Range: -4.5327

Max Act: 4.4564. Min Act: -0.1698

Data Index: 1295667 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 4.5327. Min Range: -4.5327

Max Act: 4.4580. Min Act: -0.1699

Data Index: 1546608 (Python Code)

Max Activating Token Index: 103

Text #3

Max Range: 4.5327. Min Range: -4.5327

Max Act: 4.4364. Min Act: -0.1698

Data Index: 1608098 (Python Code)

Max Activating Token Index: 610

Text #4

Max Range: 4.5327. Min Range: -4.5327

Max Act: 4.3851. Min Act: -0.1698

Data Index: 768154 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 4.5327. Min Range: -4.5327

Max Act: 4.3249. Min Act: -0.1698

Data Index: 390825 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 4.5327. Min Range: -4.5327

Max Act: 4.3341. Min Act: -0.1699

Data Index: 279389 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 4.5327. Min Range: -4.5327

Max Act: 4.3426. Min Act: -0.1698

Data Index: 916174 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 4.5327. Min Range: -4.5327

Max Act: 4.3116. Min Act: -0.1698

Data Index: 613933 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 4.5327. Min Range: -4.5327

Max Act: 4.2653. Min Act: -0.1698

Data Index: 1304076 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 4.5327. Min Range: -4.5327

Max Act: 4.2593. Min Act: -0.1698

Data Index: 1043285 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 4.5327. Min Range: -4.5327

Max Act: 4.2791. Min Act: -0.1698

Data Index: 324463 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 4.5327. Min Range: -4.5327

Max Act: 4.2533. Min Act: -0.1698

Data Index: 1343845 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 4.5327. Min Range: -4.5327

Max Act: 4.2290. Min Act: -0.1698

Data Index: 905253 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 4.5327. Min Range: -4.5327

Max Act: 4.2541. Min Act: -0.1700

Data Index: 886395 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 4.5327. Min Range: -4.5327

Max Act: 4.2175. Min Act: -0.1698

Data Index: 671751 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 4.5327. Min Range: -4.5327

Max Act: 4.2388. Min Act: -0.1698

Data Index: 875333 (C4 (Web Text))

Max Activating Token Index: 954

Text #17

Max Range: 4.5327. Min Range: -4.5327

Max Act: 4.2197. Min Act: -0.1698

Data Index: 601339 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 4.5327. Min Range: -4.5327

Max Act: 4.2331. Min Act: -0.1698

Data Index: 419032 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 4.5327. Min Range: -4.5327

Max Act: 4.2144. Min Act: -0.1698

Data Index: 716755 (C4 (Web Text))

Max Activating Token Index: 566