Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1953 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.3280. Min Range: -4.3280

Max Act: 4.3280. Min Act: -0.1700

Data Index: 294687 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 4.3280. Min Range: -4.3280

Max Act: 4.2412. Min Act: -0.1662

Data Index: 897699 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 4.3280. Min Range: -4.3280

Max Act: 4.1571. Min Act: -0.1533

Data Index: 355561 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 4.3280. Min Range: -4.3280

Max Act: 4.1702. Min Act: -0.1700

Data Index: 878393 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 4.3280. Min Range: -4.3280

Max Act: 4.1819. Min Act: -0.1700

Data Index: 968226 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 4.3280. Min Range: -4.3280

Max Act: 4.1536. Min Act: -0.1699

Data Index: 885781 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 4.3280. Min Range: -4.3280

Max Act: 4.1638. Min Act: -0.1660

Data Index: 790793 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 4.3280. Min Range: -4.3280

Max Act: 4.1325. Min Act: -0.1699

Data Index: 642123 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 4.3280. Min Range: -4.3280

Max Act: 4.1216. Min Act: -0.1542

Data Index: 203371 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 4.3280. Min Range: -4.3280

Max Act: 4.1249. Min Act: -0.1700

Data Index: 285667 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 4.3280. Min Range: -4.3280

Max Act: 4.1165. Min Act: -0.1588

Data Index: 1129180 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 4.3280. Min Range: -4.3280

Max Act: 4.1190. Min Act: -0.1514

Data Index: 422821 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 4.3280. Min Range: -4.3280

Max Act: 4.1131. Min Act: -0.1700

Data Index: 1272250 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 4.3280. Min Range: -4.3280

Max Act: 4.1168. Min Act: -0.1672

Data Index: 1336281 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 4.3280. Min Range: -4.3280

Max Act: 4.0977. Min Act: -0.1700

Data Index: 1351082 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 4.3280. Min Range: -4.3280

Max Act: 4.1070. Min Act: -0.1698

Data Index: 554014 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 4.3280. Min Range: -4.3280

Max Act: 4.1071. Min Act: -0.1700

Data Index: 973302 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 4.3280. Min Range: -4.3280

Max Act: 4.0970. Min Act: -0.1700

Data Index: 565361 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 4.3280. Min Range: -4.3280

Max Act: 4.0809. Min Act: -0.0515

Data Index: 557510 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 4.3280. Min Range: -4.3280

Max Act: 4.0813. Min Act: -0.1699

Data Index: 568657 (C4 (Web Text))

Max Activating Token Index: 685