Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 600 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.9033. Min Act: -0.1700

Data Index: 501331 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.8407. Min Act: -0.1700

Data Index: 768572 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.8720. Min Act: -0.1700

Data Index: 705225 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.8095. Min Act: -0.1700

Data Index: 713841 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.8407. Min Act: -0.1700

Data Index: 300694 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.7782. Min Act: -0.1700

Data Index: 890713 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.7782. Min Act: -0.1699

Data Index: 1564561 (Python Code)

Max Activating Token Index: 358

Text #7

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.7782. Min Act: -0.1700

Data Index: 243114 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.7469. Min Act: -0.1700

Data Index: 1084227 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.7156. Min Act: -0.1700

Data Index: 724174 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.7469. Min Act: -0.1700

Data Index: 603517 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.6843. Min Act: -0.1700

Data Index: 127124 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.6530. Min Act: -0.1700

Data Index: 423945 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.6217. Min Act: -0.1700

Data Index: 1080816 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.6217. Min Act: -0.1700

Data Index: 409172 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.6217. Min Act: -0.1700

Data Index: 1011330 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.6217. Min Act: -0.1700

Data Index: 673299 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.6530. Min Act: -0.1700

Data Index: 277189 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.6530. Min Act: -0.1700

Data Index: 1160081 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 3.9033. Min Range: -3.9033

Max Act: 3.6530. Min Act: -0.1700

Data Index: 1411764 (Python Code)

Max Activating Token Index: 819