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

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

Neuron 1137 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.2288. Min Act: -0.1700

Data Index: 1052870 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.2131. Min Act: -0.1700

Data Index: 284036 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.1659. Min Act: -0.1700

Data Index: 201892 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.1186. Min Act: -0.1700

Data Index: 302110 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.1186. Min Act: -0.1700

Data Index: 1311792 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.1029. Min Act: -0.1700

Data Index: 270383 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.0871. Min Act: -0.1700

Data Index: 152614 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.0871. Min Act: -0.1700

Data Index: 334210 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.0871. Min Act: -0.1700

Data Index: 585855 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.0556. Min Act: -0.1700

Data Index: 1233312 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.0556. Min Act: -0.1700

Data Index: 1227381 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.0398. Min Act: -0.1700

Data Index: 690432 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.0398. Min Act: -0.1700

Data Index: 728622 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.0556. Min Act: -0.1700

Data Index: 78206 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.0398. Min Act: -0.1700

Data Index: 466489 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.0398. Min Act: -0.1700

Data Index: 135581 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.0240. Min Act: -0.1700

Data Index: 270538 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 3.2288. Min Range: -3.2288

Max Act: 3.0240. Min Act: -0.1700

Data Index: 227122 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 3.2288. Min Range: -3.2288

Max Act: 2.9924. Min Act: -0.1699

Data Index: 338757 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 3.2288. Min Range: -3.2288

Max Act: 2.9924. Min Act: -0.1700

Data Index: 912972 (C4 (Web Text))

Max Activating Token Index: 140