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

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

Neuron 321 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: 5.3070. Min Range: -5.3070

Max Act: 5.3070. Min Act: -0.1700

Data Index: 1128221 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 5.3070. Min Range: -5.3070

Max Act: 5.2720. Min Act: -0.1660

Data Index: 420873 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 5.3070. Min Range: -5.3070

Max Act: 5.1959. Min Act: -0.1700

Data Index: 1075403 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 5.3070. Min Range: -5.3070

Max Act: 5.1946. Min Act: -0.1598

Data Index: 299697 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 5.3070. Min Range: -5.3070

Max Act: 5.1703. Min Act: -0.1700

Data Index: 1348195 (C4 (Web Text))

Max Activating Token Index: 567

Text #5

Max Range: 5.3070. Min Range: -5.3070

Max Act: 5.1180. Min Act: -0.1677

Data Index: 1178271 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 5.3070. Min Range: -5.3070

Max Act: 5.1485. Min Act: -0.1692

Data Index: 1259043 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 5.3070. Min Range: -5.3070

Max Act: 5.1339. Min Act: -0.1700

Data Index: 954648 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 5.3070. Min Range: -5.3070

Max Act: 5.1362. Min Act: -0.1700

Data Index: 1276280 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 5.3070. Min Range: -5.3070

Max Act: 5.0847. Min Act: -0.1598

Data Index: 761936 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 5.3070. Min Range: -5.3070

Max Act: 5.0962. Min Act: -0.1700

Data Index: 920167 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 5.3070. Min Range: -5.3070

Max Act: 5.1064. Min Act: -0.1699

Data Index: 370359 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 5.3070. Min Range: -5.3070

Max Act: 5.1136. Min Act: -0.1598

Data Index: 756635 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 5.3070. Min Range: -5.3070

Max Act: 5.0864. Min Act: -0.1700

Data Index: 696181 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 5.3070. Min Range: -5.3070

Max Act: 5.0828. Min Act: -0.1598

Data Index: 417347 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 5.3070. Min Range: -5.3070

Max Act: 5.0645. Min Act: -0.1699

Data Index: 957228 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 5.3070. Min Range: -5.3070

Max Act: 5.0612. Min Act: -0.1598

Data Index: 1321576 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 5.3070. Min Range: -5.3070

Max Act: 5.0758. Min Act: -0.1700

Data Index: 1346492 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 5.3070. Min Range: -5.3070

Max Act: 5.0521. Min Act: -0.1700

Data Index: 974333 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 5.3070. Min Range: -5.3070

Max Act: 5.0307. Min Act: -0.1598

Data Index: 825435 (C4 (Web Text))

Max Activating Token Index: 271