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

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

Neuron 1891 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: 11.7007. Min Range: -11.7007

Max Act: 11.7007. Min Act: -0.1213

Data Index: 20748 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 11.7007. Min Range: -11.7007

Max Act: 11.3277. Min Act: -0.1317

Data Index: 1254776 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 11.7007. Min Range: -11.7007

Max Act: 11.2692. Min Act: -0.1681

Data Index: 363700 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 11.7007. Min Range: -11.7007

Max Act: 11.0912. Min Act: -0.1700

Data Index: 622625 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 11.7007. Min Range: -11.7007

Max Act: 11.0599. Min Act: -0.1700

Data Index: 416253 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 11.7007. Min Range: -11.7007

Max Act: 10.8799. Min Act: -0.1577

Data Index: 724140 (C4 (Web Text))

Max Activating Token Index: 602

Text #6

Max Range: 11.7007. Min Range: -11.7007

Max Act: 10.8465. Min Act: -0.1699

Data Index: 497883 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 11.7007. Min Range: -11.7007

Max Act: 10.7349. Min Act: -0.1683

Data Index: 1140488 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 11.7007. Min Range: -11.7007

Max Act: 10.7824. Min Act: -0.1699

Data Index: 1090375 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 11.7007. Min Range: -11.7007

Max Act: 10.7126. Min Act: -0.0738

Data Index: 809368 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 11.7007. Min Range: -11.7007

Max Act: 10.6860. Min Act: -0.1663

Data Index: 393532 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 11.7007. Min Range: -11.7007

Max Act: 10.7135. Min Act: -0.1700

Data Index: 1109117 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 11.7007. Min Range: -11.7007

Max Act: 10.6475. Min Act: -0.1699

Data Index: 155300 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 11.7007. Min Range: -11.7007

Max Act: 10.4892. Min Act: -0.0273

Data Index: 482912 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 11.7007. Min Range: -11.7007

Max Act: 10.4244. Min Act: -0.0273

Data Index: 737904 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 11.7007. Min Range: -11.7007

Max Act: 10.4593. Min Act: -0.0273

Data Index: 1220112 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 11.7007. Min Range: -11.7007

Max Act: 10.4109. Min Act: -0.1700

Data Index: 978492 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 11.7007. Min Range: -11.7007

Max Act: 10.3734. Min Act: -0.1700

Data Index: 1104778 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 11.7007. Min Range: -11.7007

Max Act: 10.3758. Min Act: -0.1179

Data Index: 1174126 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 11.7007. Min Range: -11.7007

Max Act: 10.2943. Min Act: -0.1700

Data Index: 901523 (C4 (Web Text))

Max Activating Token Index: 772