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

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

Neuron 1315 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: 3.7600. Min Range: -3.7600

Max Act: 3.7600. Min Act: -0.1700

Data Index: 510368 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 3.7600. Min Range: -3.7600

Max Act: 3.7252. Min Act: -0.1700

Data Index: 1244624 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 3.7600. Min Range: -3.7600

Max Act: 3.7271. Min Act: -0.1700

Data Index: 161793 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 3.7600. Min Range: -3.7600

Max Act: 3.6483. Min Act: -0.1700

Data Index: 771141 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 3.7600. Min Range: -3.7600

Max Act: 3.5163. Min Act: -0.1700

Data Index: 1391817 (Python Code)

Max Activating Token Index: 612

Text #5

Max Range: 3.7600. Min Range: -3.7600

Max Act: 3.5298. Min Act: -0.1700

Data Index: 864064 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 3.7600. Min Range: -3.7600

Max Act: 3.4846. Min Act: -0.1700

Data Index: 1609345 (Python Code)

Max Activating Token Index: 41

Text #7

Max Range: 3.7600. Min Range: -3.7600

Max Act: 3.4467. Min Act: -0.1700

Data Index: 183035 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 3.7600. Min Range: -3.7600

Max Act: 3.4534. Min Act: -0.1700

Data Index: 1251388 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 3.7600. Min Range: -3.7600

Max Act: 3.4344. Min Act: -0.1700

Data Index: 1388567 (Python Code)

Max Activating Token Index: 13

Text #10

Max Range: 3.7600. Min Range: -3.7600

Max Act: 3.3910. Min Act: -0.1700

Data Index: 1395243 (Python Code)

Max Activating Token Index: 961

Text #11

Max Range: 3.7600. Min Range: -3.7600

Max Act: 3.4251. Min Act: -0.1700

Data Index: 1437794 (Python Code)

Max Activating Token Index: 805

Text #12

Max Range: 3.7600. Min Range: -3.7600

Max Act: 3.4509. Min Act: -0.1700

Data Index: 619088 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 3.7600. Min Range: -3.7600

Max Act: 3.4537. Min Act: -0.1700

Data Index: 611501 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 3.7600. Min Range: -3.7600

Max Act: 3.4162. Min Act: -0.1700

Data Index: 1406471 (Python Code)

Max Activating Token Index: 58

Text #15

Max Range: 3.7600. Min Range: -3.7600

Max Act: 3.4205. Min Act: -0.1700

Data Index: 1535993 (Python Code)

Max Activating Token Index: 372

Text #16

Max Range: 3.7600. Min Range: -3.7600

Max Act: 3.4227. Min Act: -0.1700

Data Index: 122144 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 3.7600. Min Range: -3.7600

Max Act: 3.4193. Min Act: -0.1700

Data Index: 1089613 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 3.7600. Min Range: -3.7600

Max Act: 3.4049. Min Act: -0.1700

Data Index: 464928 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 3.7600. Min Range: -3.7600

Max Act: 3.3975. Min Act: -0.1700

Data Index: 1557561 (Python Code)

Max Activating Token Index: 18