Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 788 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.5048. Min Range: -3.5048

Max Act: 3.5048. Min Act: -0.1700

Data Index: 1558834 (Python Code)

Max Activating Token Index: 575

Text #1

Max Range: 3.5048. Min Range: -3.5048

Max Act: 3.4892. Min Act: -0.1700

Data Index: 949820 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 3.5048. Min Range: -3.5048

Max Act: 3.4265. Min Act: -0.1700

Data Index: 511765 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 3.5048. Min Range: -3.5048

Max Act: 3.4108. Min Act: -0.1700

Data Index: 1527198 (Python Code)

Max Activating Token Index: 70

Text #4

Max Range: 3.5048. Min Range: -3.5048

Max Act: 3.3951. Min Act: -0.1700

Data Index: 24401 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 3.5048. Min Range: -3.5048

Max Act: 3.3951. Min Act: -0.1700

Data Index: 309958 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 3.5048. Min Range: -3.5048

Max Act: 3.3951. Min Act: -0.1700

Data Index: 1581434 (Python Code)

Max Activating Token Index: 278

Text #7

Max Range: 3.5048. Min Range: -3.5048

Max Act: 3.3637. Min Act: -0.1700

Data Index: 509597 (C4 (Web Text))

Max Activating Token Index: 264

Text #8

Max Range: 3.5048. Min Range: -3.5048

Max Act: 3.3323. Min Act: -0.1700

Data Index: 205657 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 3.5048. Min Range: -3.5048

Max Act: 3.3480. Min Act: -0.1700

Data Index: 1187196 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 3.5048. Min Range: -3.5048

Max Act: 3.3323. Min Act: -0.1700

Data Index: 66194 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 3.5048. Min Range: -3.5048

Max Act: 3.3323. Min Act: -0.1700

Data Index: 297511 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 3.5048. Min Range: -3.5048

Max Act: 3.3166. Min Act: -0.1700

Data Index: 1277271 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 3.5048. Min Range: -3.5048

Max Act: 3.3323. Min Act: -0.1700

Data Index: 472152 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 3.5048. Min Range: -3.5048

Max Act: 3.3323. Min Act: -0.1700

Data Index: 761340 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 3.5048. Min Range: -3.5048

Max Act: 3.3166. Min Act: -0.1700

Data Index: 1413388 (Python Code)

Max Activating Token Index: 498

Text #16

Max Range: 3.5048. Min Range: -3.5048

Max Act: 3.3166. Min Act: -0.1700

Data Index: 1511043 (Python Code)

Max Activating Token Index: 974

Text #17

Max Range: 3.5048. Min Range: -3.5048

Max Act: 3.3166. Min Act: -0.1700

Data Index: 46518 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 3.5048. Min Range: -3.5048

Max Act: 3.3323. Min Act: -0.1700

Data Index: 438114 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 3.5048. Min Range: -3.5048

Max Act: 3.3323. Min Act: -0.1700

Data Index: 558864 (C4 (Web Text))

Max Activating Token Index: 624