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

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

Neuron 1402 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5970. Min Range: -5.5970

Max Act: 5.5970. Min Act: -0.1700

Data Index: 687968 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 5.5970. Min Range: -5.5970

Max Act: 5.5501. Min Act: -0.1700

Data Index: 837579 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 5.5970. Min Range: -5.5970

Max Act: 5.5345. Min Act: -0.1700

Data Index: 719208 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 5.5970. Min Range: -5.5970

Max Act: 5.4876. Min Act: -0.1700

Data Index: 882316 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 5.5970. Min Range: -5.5970

Max Act: 5.4564. Min Act: -0.1700

Data Index: 933348 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 5.5970. Min Range: -5.5970

Max Act: 5.4720. Min Act: -0.1700

Data Index: 327811 (C4 (Web Text))

Max Activating Token Index: 653

Text #6

Max Range: 5.5970. Min Range: -5.5970

Max Act: 5.4720. Min Act: -0.1700

Data Index: 85148 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 5.5970. Min Range: -5.5970

Max Act: 5.4876. Min Act: -0.1700

Data Index: 525534 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 5.5970. Min Range: -5.5970

Max Act: 5.4564. Min Act: -0.1700

Data Index: 863510 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 5.5970. Min Range: -5.5970

Max Act: 5.4407. Min Act: -0.1700

Data Index: 698648 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 5.5970. Min Range: -5.5970

Max Act: 5.4564. Min Act: -0.1700

Data Index: 345097 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 5.5970. Min Range: -5.5970

Max Act: 5.4407. Min Act: -0.1700

Data Index: 906507 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 5.5970. Min Range: -5.5970

Max Act: 5.3782. Min Act: -0.1700

Data Index: 248925 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 5.5970. Min Range: -5.5970

Max Act: 5.4720. Min Act: -0.1700

Data Index: 341065 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 5.5970. Min Range: -5.5970

Max Act: 5.4407. Min Act: -0.1700

Data Index: 1335892 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 5.5970. Min Range: -5.5970

Max Act: 5.4407. Min Act: -0.1700

Data Index: 547058 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 5.5970. Min Range: -5.5970

Max Act: 5.3782. Min Act: -0.1700

Data Index: 657665 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 5.5970. Min Range: -5.5970

Max Act: 5.4095. Min Act: -0.1700

Data Index: 566829 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 5.5970. Min Range: -5.5970

Max Act: 5.4407. Min Act: -0.1700

Data Index: 18007 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 5.5970. Min Range: -5.5970

Max Act: 5.3782. Min Act: -0.1700

Data Index: 861066 (C4 (Web Text))

Max Activating Token Index: 91