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

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

Neuron 347 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.7255. Min Act: -0.1700

Data Index: 915308 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.9130. Min Act: -0.1700

Data Index: 476018 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.8818. Min Act: -0.1700

Data Index: 225156 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.8193. Min Act: -0.1700

Data Index: 1082657 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.8193. Min Act: -0.1700

Data Index: 65147 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.8505. Min Act: -0.1700

Data Index: 762193 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.8193. Min Act: -0.1700

Data Index: 694811 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.8505. Min Act: -0.1700

Data Index: 658976 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.7880. Min Act: -0.1700

Data Index: 983056 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.7255. Min Act: -0.1700

Data Index: 253762 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.7880. Min Act: -0.1700

Data Index: 781321 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.7880. Min Act: -0.1700

Data Index: 400626 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.7568. Min Act: -0.1700

Data Index: 38546 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.8505. Min Act: -0.1700

Data Index: 396595 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.7880. Min Act: -0.1700

Data Index: 1114299 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.7880. Min Act: -0.1700

Data Index: 417468 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.8193. Min Act: -0.1700

Data Index: 1275100 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.8505. Min Act: -0.1700

Data Index: 968371 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.6630. Min Act: -0.1700

Data Index: 519519 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 5.9130. Min Range: -5.9130

Max Act: 5.7880. Min Act: -0.1700

Data Index: 1078658 (C4 (Web Text))

Max Activating Token Index: 119