Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1770 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.3126. Min Act: -0.1700

Data Index: 17163 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.2812. Min Act: -0.1700

Data Index: 377238 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.2341. Min Act: -0.1700

Data Index: 1599113 (Python Code)

Max Activating Token Index: 119

Text #3

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.2341. Min Act: -0.1700

Data Index: 558358 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.2026. Min Act: -0.1700

Data Index: 1163645 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.2026. Min Act: -0.1700

Data Index: 516506 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.1869. Min Act: -0.1700

Data Index: 1325232 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.1711. Min Act: -0.1700

Data Index: 613712 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.2026. Min Act: -0.1700

Data Index: 459986 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.2026. Min Act: -0.1700

Data Index: 947245 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.1554. Min Act: -0.1700

Data Index: 861215 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.1711. Min Act: -0.1700

Data Index: 657770 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.1869. Min Act: -0.1700

Data Index: 449657 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.1869. Min Act: -0.1700

Data Index: 745056 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.1869. Min Act: -0.1700

Data Index: 625502 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.1711. Min Act: -0.1700

Data Index: 369838 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.1869. Min Act: -0.1700

Data Index: 338414 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.1554. Min Act: -0.1700

Data Index: 423623 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.1711. Min Act: -0.1700

Data Index: 484965 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 3.3126. Min Range: -3.3126

Max Act: 3.1869. Min Act: -0.1700

Data Index: 200096 (C4 (Web Text))

Max Activating Token Index: 781