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

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

Neuron 61 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: 3.9920. Min Range: -3.9920

Max Act: 3.9920. Min Act: -0.1700

Data Index: 406430 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 3.9920. Min Range: -3.9920

Max Act: 3.9750. Min Act: -0.1700

Data Index: 281916 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 3.9920. Min Range: -3.9920

Max Act: 3.8929. Min Act: -0.1700

Data Index: 622110 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 3.9920. Min Range: -3.9920

Max Act: 3.8661. Min Act: -0.1700

Data Index: 1296230 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 3.9920. Min Range: -3.9920

Max Act: 3.8544. Min Act: -0.1700

Data Index: 729870 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 3.9920. Min Range: -3.9920

Max Act: 3.8353. Min Act: -0.1700

Data Index: 1046831 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 3.9920. Min Range: -3.9920

Max Act: 3.7991. Min Act: -0.1700

Data Index: 1072965 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 3.9920. Min Range: -3.9920

Max Act: 3.7922. Min Act: -0.1699

Data Index: 701252 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 3.9920. Min Range: -3.9920

Max Act: 3.8171. Min Act: -0.1700

Data Index: 900104 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 3.9920. Min Range: -3.9920

Max Act: 3.7780. Min Act: -0.1700

Data Index: 1078511 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 3.9920. Min Range: -3.9920

Max Act: 3.7468. Min Act: -0.1700

Data Index: 1330696 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 3.9920. Min Range: -3.9920

Max Act: 3.7203. Min Act: -0.1700

Data Index: 907290 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 3.9920. Min Range: -3.9920

Max Act: 3.7187. Min Act: -0.1700

Data Index: 777046 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 3.9920. Min Range: -3.9920

Max Act: 3.7084. Min Act: -0.1700

Data Index: 1017163 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 3.9920. Min Range: -3.9920

Max Act: 3.7082. Min Act: -0.1700

Data Index: 430875 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 3.9920. Min Range: -3.9920

Max Act: 3.6935. Min Act: -0.1700

Data Index: 1006450 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 3.9920. Min Range: -3.9920

Max Act: 3.6713. Min Act: -0.1700

Data Index: 1233476 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 3.9920. Min Range: -3.9920

Max Act: 3.6665. Min Act: -0.1700

Data Index: 937967 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 3.9920. Min Range: -3.9920

Max Act: 3.6603. Min Act: -0.1700

Data Index: 304770 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 3.9920. Min Range: -3.9920

Max Act: 3.6938. Min Act: -0.1700

Data Index: 515216 (C4 (Web Text))

Max Activating Token Index: 899