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

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

Neuron 1101 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: 3.4257. Min Range: -3.4257

Max Act: 3.4257. Min Act: -0.1700

Data Index: 965268 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 3.4257. Min Range: -3.4257

Max Act: 3.2502. Min Act: -0.1700

Data Index: 883271 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 3.4257. Min Range: -3.4257

Max Act: 3.2275. Min Act: -0.1700

Data Index: 1879 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 3.4257. Min Range: -3.4257

Max Act: 3.2228. Min Act: -0.1700

Data Index: 991881 (C4 (Web Text))

Max Activating Token Index: 790

Text #4

Max Range: 3.4257. Min Range: -3.4257

Max Act: 3.2047. Min Act: -0.1700

Data Index: 516116 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 3.4257. Min Range: -3.4257

Max Act: 3.1947. Min Act: -0.1700

Data Index: 1199850 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 3.4257. Min Range: -3.4257

Max Act: 3.1999. Min Act: -0.1700

Data Index: 940950 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 3.4257. Min Range: -3.4257

Max Act: 3.1916. Min Act: -0.1700

Data Index: 624451 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 3.4257. Min Range: -3.4257

Max Act: 3.1586. Min Act: -0.1700

Data Index: 873064 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 3.4257. Min Range: -3.4257

Max Act: 3.1600. Min Act: -0.1700

Data Index: 1197946 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 3.4257. Min Range: -3.4257

Max Act: 3.1762. Min Act: -0.1700

Data Index: 934534 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 3.4257. Min Range: -3.4257

Max Act: 3.1621. Min Act: -0.1700

Data Index: 911731 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 3.4257. Min Range: -3.4257

Max Act: 3.1636. Min Act: -0.1700

Data Index: 211627 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 3.4257. Min Range: -3.4257

Max Act: 3.1504. Min Act: -0.1700

Data Index: 528622 (C4 (Web Text))

Max Activating Token Index: 991

Text #14

Max Range: 3.4257. Min Range: -3.4257

Max Act: 3.1348. Min Act: -0.1700

Data Index: 714237 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 3.4257. Min Range: -3.4257

Max Act: 3.1419. Min Act: -0.1700

Data Index: 669221 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 3.4257. Min Range: -3.4257

Max Act: 3.1360. Min Act: -0.1700

Data Index: 100955 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 3.4257. Min Range: -3.4257

Max Act: 3.1346. Min Act: -0.1700

Data Index: 29422 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 3.4257. Min Range: -3.4257

Max Act: 3.1151. Min Act: -0.1700

Data Index: 56245 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 3.4257. Min Range: -3.4257

Max Act: 3.1282. Min Act: -0.1700

Data Index: 20228 (C4 (Web Text))

Max Activating Token Index: 228