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

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

Neuron 1490 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: 3.6609. Min Range: -3.6609

Max Act: 3.6509. Min Act: -0.1700

Data Index: 754547 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.6609. Min Act: -0.1700

Data Index: 1172841 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.5403. Min Act: -0.1700

Data Index: 196356 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.5388. Min Act: -0.1700

Data Index: 925358 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.5413. Min Act: -0.1700

Data Index: 51251 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.4852. Min Act: -0.1700

Data Index: 146513 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.4909. Min Act: -0.1700

Data Index: 1166071 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.4668. Min Act: -0.1700

Data Index: 1322865 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.4431. Min Act: -0.1700

Data Index: 1621009 (Python Code)

Max Activating Token Index: 243

Text #9

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.4342. Min Act: -0.1700

Data Index: 720666 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.4303. Min Act: -0.1700

Data Index: 244146 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.4440. Min Act: -0.1700

Data Index: 687515 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.4157. Min Act: -0.1700

Data Index: 1035573 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.4303. Min Act: -0.1700

Data Index: 1182853 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.4123. Min Act: -0.1700

Data Index: 555712 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.4151. Min Act: -0.1700

Data Index: 457284 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.4257. Min Act: -0.1699

Data Index: 1630962 (Python Code)

Max Activating Token Index: 416

Text #17

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.4017. Min Act: -0.1700

Data Index: 1346085 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.4055. Min Act: -0.1700

Data Index: 141255 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.4199. Min Act: -0.1700

Data Index: 953500 (C4 (Web Text))

Max Activating Token Index: 676