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

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

Neuron 296 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: 3.7324. Min Range: -3.7324

Max Act: 3.7324. Min Act: -0.1700

Data Index: 1093836 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.7138. Min Act: -0.1700

Data Index: 1196138 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.7105. Min Act: -0.1698

Data Index: 1406504 (Python Code)

Max Activating Token Index: 67

Text #3

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.7124. Min Act: -0.1700

Data Index: 64711 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.6686. Min Act: -0.1700

Data Index: 1200815 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.6324. Min Act: -0.1700

Data Index: 1181807 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.6264. Min Act: -0.1699

Data Index: 1337666 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.5945. Min Act: -0.1699

Data Index: 745164 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.6263. Min Act: -0.1700

Data Index: 640123 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.6246. Min Act: -0.1700

Data Index: 556206 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.5940. Min Act: -0.1700

Data Index: 469279 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.5955. Min Act: -0.1700

Data Index: 1539090 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.5742. Min Act: -0.1692

Data Index: 386968 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.5910. Min Act: -0.1700

Data Index: 835831 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.5733. Min Act: -0.1700

Data Index: 484933 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.5796. Min Act: -0.1700

Data Index: 152934 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.5870. Min Act: -0.1698

Data Index: 1100578 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.5648. Min Act: -0.1700

Data Index: 62311 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.5494. Min Act: -0.1700

Data Index: 366136 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.7324. Min Range: -3.7324

Max Act: 3.5486. Min Act: -0.1700

Data Index: 653989 (C4 (Web Text))

Max Activating Token Index: 839