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

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

Neuron 1512 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: 3.3380. Min Range: -3.3380

Max Act: 3.3380. Min Act: -0.1700

Data Index: 1030654 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 3.3380. Min Range: -3.3380

Max Act: 3.3053. Min Act: -0.1700

Data Index: 1101615 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 3.3380. Min Range: -3.3380

Max Act: 3.2691. Min Act: -0.1700

Data Index: 613328 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 3.3380. Min Range: -3.3380

Max Act: 3.2080. Min Act: -0.1700

Data Index: 599639 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 3.3380. Min Range: -3.3380

Max Act: 3.2299. Min Act: -0.1700

Data Index: 244697 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.3380. Min Range: -3.3380

Max Act: 3.2150. Min Act: -0.1700

Data Index: 1030048 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.3380. Min Range: -3.3380

Max Act: 3.2149. Min Act: -0.1700

Data Index: 898940 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.3380. Min Range: -3.3380

Max Act: 3.1847. Min Act: -0.1691

Data Index: 139278 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 3.3380. Min Range: -3.3380

Max Act: 3.1945. Min Act: -0.1700

Data Index: 23413 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.3380. Min Range: -3.3380

Max Act: 3.1889. Min Act: -0.1700

Data Index: 1219954 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.3380. Min Range: -3.3380

Max Act: 3.1705. Min Act: -0.1700

Data Index: 379046 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 3.3380. Min Range: -3.3380

Max Act: 3.1700. Min Act: -0.1700

Data Index: 374222 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 3.3380. Min Range: -3.3380

Max Act: 3.1457. Min Act: -0.1700

Data Index: 989006 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 3.3380. Min Range: -3.3380

Max Act: 3.1491. Min Act: -0.1700

Data Index: 1193382 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 3.3380. Min Range: -3.3380

Max Act: 3.1092. Min Act: -0.1700

Data Index: 772431 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 3.3380. Min Range: -3.3380

Max Act: 3.1170. Min Act: -0.1700

Data Index: 577061 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 3.3380. Min Range: -3.3380

Max Act: 3.1227. Min Act: -0.1700

Data Index: 233816 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 3.3380. Min Range: -3.3380

Max Act: 3.1295. Min Act: -0.1700

Data Index: 146184 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.3380. Min Range: -3.3380

Max Act: 3.1369. Min Act: -0.1700

Data Index: 360676 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 3.3380. Min Range: -3.3380

Max Act: 3.1259. Min Act: -0.1700

Data Index: 141970 (C4 (Web Text))

Max Activating Token Index: 1023