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

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

Neuron 808 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: 4.2623. Min Range: -4.2623

Max Act: 4.2251. Min Act: -0.1700

Data Index: 1655480 (Python Code)

Max Activating Token Index: 549

Text #1

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.2623. Min Act: -0.1700

Data Index: 1586737 (Python Code)

Max Activating Token Index: 528

Text #2

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.1998. Min Act: -0.1700

Data Index: 447124 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.2049. Min Act: -0.1700

Data Index: 1144582 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.1749. Min Act: -0.1700

Data Index: 1209136 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.1926. Min Act: -0.1700

Data Index: 564768 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.1160. Min Act: -0.1700

Data Index: 1266143 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.1770. Min Act: -0.1700

Data Index: 520382 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.1132. Min Act: -0.1700

Data Index: 1204121 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.1324. Min Act: -0.1700

Data Index: 1528718 (Python Code)

Max Activating Token Index: 922

Text #10

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.1276. Min Act: -0.1700

Data Index: 1125676 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.1543. Min Act: -0.1700

Data Index: 235606 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.1009. Min Act: -0.1700

Data Index: 469601 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.0949. Min Act: -0.1700

Data Index: 413105 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.0833. Min Act: -0.1700

Data Index: 695786 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.0274. Min Act: -0.1700

Data Index: 637971 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.0837. Min Act: -0.1700

Data Index: 345657 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.0854. Min Act: -0.1700

Data Index: 1182008 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.0521. Min Act: -0.1700

Data Index: 820365 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 4.2623. Min Range: -4.2623

Max Act: 4.0996. Min Act: -0.1700

Data Index: 11901 (C4 (Web Text))

Max Activating Token Index: 378