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

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

Neuron 1786 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: 3.5321. Min Range: -3.5321

Max Act: 3.5321. Min Act: -0.1700

Data Index: 365008 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.3694. Min Act: -0.1700

Data Index: 1197441 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.3525. Min Act: -0.1700

Data Index: 1518970 (Python Code)

Max Activating Token Index: 876

Text #3

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.3423. Min Act: -0.1700

Data Index: 1040869 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.3210. Min Act: -0.1700

Data Index: 208372 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.2434. Min Act: -0.1700

Data Index: 16352 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.2317. Min Act: -0.1700

Data Index: 1504980 (Python Code)

Max Activating Token Index: 46

Text #7

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.2412. Min Act: -0.1700

Data Index: 83660 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.2249. Min Act: -0.1700

Data Index: 1219185 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.2121. Min Act: -0.1700

Data Index: 110001 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.2030. Min Act: -0.1700

Data Index: 784498 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.2018. Min Act: -0.1700

Data Index: 816430 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.1876. Min Act: -0.1700

Data Index: 487989 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.1878. Min Act: -0.1700

Data Index: 995627 (C4 (Web Text))

Max Activating Token Index: 322

Text #14

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.1826. Min Act: -0.1700

Data Index: 833694 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.1676. Min Act: -0.1700

Data Index: 294692 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.1505. Min Act: -0.1700

Data Index: 778372 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.1498. Min Act: -0.1700

Data Index: 1171282 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.1619. Min Act: -0.1700

Data Index: 518565 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 3.5321. Min Range: -3.5321

Max Act: 3.1335. Min Act: -0.1700

Data Index: 696028 (C4 (Web Text))

Max Activating Token Index: 879