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

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

Neuron 152 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3287. Min Range: -5.3287

Max Act: 5.2350. Min Act: -0.1700

Data Index: 872517 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 5.3287. Min Range: -5.3287

Max Act: 5.3287. Min Act: -0.1700

Data Index: 900499 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 5.3287. Min Range: -5.3287

Max Act: 5.3287. Min Act: -0.1700

Data Index: 1322947 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 5.3287. Min Range: -5.3287

Max Act: 5.1100. Min Act: -0.1700

Data Index: 578946 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 5.3287. Min Range: -5.3287

Max Act: 5.1412. Min Act: -0.1700

Data Index: 1069036 (C4 (Web Text))

Max Activating Token Index: 412

Text #5

Max Range: 5.3287. Min Range: -5.3287

Max Act: 5.2037. Min Act: -0.1700

Data Index: 553383 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 5.3287. Min Range: -5.3287

Max Act: 5.1100. Min Act: -0.1700

Data Index: 35690 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 5.3287. Min Range: -5.3287

Max Act: 5.0475. Min Act: -0.1700

Data Index: 1052300 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 5.3287. Min Range: -5.3287

Max Act: 5.0787. Min Act: -0.1700

Data Index: 722316 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 5.3287. Min Range: -5.3287

Max Act: 5.0475. Min Act: -0.1700

Data Index: 371688 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 5.3287. Min Range: -5.3287

Max Act: 5.0787. Min Act: -0.1700

Data Index: 740460 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 5.3287. Min Range: -5.3287

Max Act: 4.9225. Min Act: -0.1700

Data Index: 1298804 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 5.3287. Min Range: -5.3287

Max Act: 5.0162. Min Act: -0.1700

Data Index: 1178773 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 5.3287. Min Range: -5.3287

Max Act: 4.8912. Min Act: -0.1700

Data Index: 83239 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 5.3287. Min Range: -5.3287

Max Act: 4.9537. Min Act: -0.1700

Data Index: 275499 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 5.3287. Min Range: -5.3287

Max Act: 4.9225. Min Act: -0.1700

Data Index: 966260 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 5.3287. Min Range: -5.3287

Max Act: 5.0787. Min Act: -0.1700

Data Index: 409990 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 5.3287. Min Range: -5.3287

Max Act: 5.0162. Min Act: -0.1700

Data Index: 427472 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 5.3287. Min Range: -5.3287

Max Act: 4.9537. Min Act: -0.1700

Data Index: 784331 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 5.3287. Min Range: -5.3287

Max Act: 4.9225. Min Act: -0.1700

Data Index: 532642 (C4 (Web Text))

Max Activating Token Index: 1006