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

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

Neuron 327 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: 3.5403. Min Range: -3.5403

Max Act: 3.4776. Min Act: -0.1700

Data Index: 381926 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.5089. Min Act: -0.1700

Data Index: 811294 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.5403. Min Act: -0.1700

Data Index: 216663 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.4619. Min Act: -0.1700

Data Index: 14273 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.4462. Min Act: -0.1700

Data Index: 827033 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.4933. Min Act: -0.1700

Data Index: 356242 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.4462. Min Act: -0.1700

Data Index: 1002581 (C4 (Web Text))

Max Activating Token Index: 532

Text #7

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.4776. Min Act: -0.1700

Data Index: 1231949 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.4462. Min Act: -0.1700

Data Index: 951204 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.4306. Min Act: -0.1700

Data Index: 700962 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.3835. Min Act: -0.1700

Data Index: 660804 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.3992. Min Act: -0.1700

Data Index: 348376 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.3992. Min Act: -0.1700

Data Index: 641706 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.3992. Min Act: -0.1700

Data Index: 82401 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.3678. Min Act: -0.1700

Data Index: 1286617 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.3678. Min Act: -0.1700

Data Index: 887297 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.3207. Min Act: -0.1700

Data Index: 696856 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.3521. Min Act: -0.1700

Data Index: 1206086 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.3521. Min Act: -0.1700

Data Index: 1185389 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 3.5403. Min Range: -3.5403

Max Act: 3.3521. Min Act: -0.1700

Data Index: 813199 (C4 (Web Text))

Max Activating Token Index: 645