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

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

Neuron 1194 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: 3.3618. Min Range: -3.3618

Max Act: 3.3618. Min Act: -0.1700

Data Index: 656523 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 3.3618. Min Range: -3.3618

Max Act: 3.2800. Min Act: -0.1700

Data Index: 123540 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 3.3618. Min Range: -3.3618

Max Act: 3.2826. Min Act: -0.1700

Data Index: 490114 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 3.3618. Min Range: -3.3618

Max Act: 3.2610. Min Act: -0.1700

Data Index: 309539 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 3.3618. Min Range: -3.3618

Max Act: 3.2655. Min Act: -0.1700

Data Index: 396479 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 3.3618. Min Range: -3.3618

Max Act: 3.2434. Min Act: -0.1700

Data Index: 1106365 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 3.3618. Min Range: -3.3618

Max Act: 3.2387. Min Act: -0.1700

Data Index: 801572 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 3.3618. Min Range: -3.3618

Max Act: 3.2675. Min Act: -0.1700

Data Index: 257325 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 3.3618. Min Range: -3.3618

Max Act: 3.2766. Min Act: -0.1700

Data Index: 534455 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 3.3618. Min Range: -3.3618

Max Act: 3.2574. Min Act: -0.1700

Data Index: 843736 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 3.3618. Min Range: -3.3618

Max Act: 3.2274. Min Act: -0.1700

Data Index: 1018876 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 3.3618. Min Range: -3.3618

Max Act: 3.2315. Min Act: -0.1700

Data Index: 1033747 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 3.3618. Min Range: -3.3618

Max Act: 3.2204. Min Act: -0.1700

Data Index: 306610 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 3.3618. Min Range: -3.3618

Max Act: 3.2169. Min Act: -0.1700

Data Index: 190808 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 3.3618. Min Range: -3.3618

Max Act: 3.2001. Min Act: -0.1700

Data Index: 747443 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 3.3618. Min Range: -3.3618

Max Act: 3.1941. Min Act: -0.1700

Data Index: 986110 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 3.3618. Min Range: -3.3618

Max Act: 3.1965. Min Act: -0.1700

Data Index: 194515 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 3.3618. Min Range: -3.3618

Max Act: 3.2105. Min Act: -0.1700

Data Index: 1166302 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 3.3618. Min Range: -3.3618

Max Act: 3.1853. Min Act: -0.1700

Data Index: 992786 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 3.3618. Min Range: -3.3618

Max Act: 3.1800. Min Act: -0.1700

Data Index: 644645 (C4 (Web Text))

Max Activating Token Index: 373