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

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

Neuron 1209 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: 3.9616. Min Range: -3.9616

Max Act: 3.9616. Min Act: -0.1700

Data Index: 904197 (C4 (Web Text))

Max Activating Token Index: 589

Text #1

Max Range: 3.9616. Min Range: -3.9616

Max Act: 3.9405. Min Act: -0.1700

Data Index: 555332 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 3.9616. Min Range: -3.9616

Max Act: 3.8656. Min Act: -0.1700

Data Index: 810322 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 3.9616. Min Range: -3.9616

Max Act: 3.7889. Min Act: -0.1700

Data Index: 1291875 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 3.9616. Min Range: -3.9616

Max Act: 3.7778. Min Act: -0.1700

Data Index: 1082876 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 3.9616. Min Range: -3.9616

Max Act: 3.7739. Min Act: -0.1700

Data Index: 806853 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 3.9616. Min Range: -3.9616

Max Act: 3.7627. Min Act: -0.1700

Data Index: 1265839 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 3.9616. Min Range: -3.9616

Max Act: 3.7475. Min Act: -0.1700

Data Index: 731142 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 3.9616. Min Range: -3.9616

Max Act: 3.7465. Min Act: -0.1700

Data Index: 1133338 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 3.9616. Min Range: -3.9616

Max Act: 3.7088. Min Act: -0.1700

Data Index: 854360 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 3.9616. Min Range: -3.9616

Max Act: 3.6971. Min Act: -0.1700

Data Index: 879282 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 3.9616. Min Range: -3.9616

Max Act: 3.6797. Min Act: -0.1700

Data Index: 934523 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 3.9616. Min Range: -3.9616

Max Act: 3.6482. Min Act: -0.1700

Data Index: 1004565 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 3.9616. Min Range: -3.9616

Max Act: 3.6534. Min Act: -0.1700

Data Index: 1282742 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 3.9616. Min Range: -3.9616

Max Act: 3.6331. Min Act: -0.1700

Data Index: 12941 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 3.9616. Min Range: -3.9616

Max Act: 3.6260. Min Act: -0.1700

Data Index: 422323 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 3.9616. Min Range: -3.9616

Max Act: 3.5995. Min Act: -0.1700

Data Index: 460160 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 3.9616. Min Range: -3.9616

Max Act: 3.6198. Min Act: -0.1700

Data Index: 97238 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 3.9616. Min Range: -3.9616

Max Act: 3.6258. Min Act: -0.1700

Data Index: 1099505 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 3.9616. Min Range: -3.9616

Max Act: 3.6094. Min Act: -0.1700

Data Index: 1356014 (C4 (Web Text))

Max Activating Token Index: 408