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

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

Neuron 1573 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: 5.7297. Min Range: -5.7297

Max Act: 5.7297. Min Act: -0.1700

Data Index: 1322752 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 5.7297. Min Range: -5.7297

Max Act: 5.6929. Min Act: -0.1700

Data Index: 4737 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 5.7297. Min Range: -5.7297

Max Act: 5.6518. Min Act: -0.1700

Data Index: 128506 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 5.7297. Min Range: -5.7297

Max Act: 5.6004. Min Act: -0.1700

Data Index: 255622 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 5.7297. Min Range: -5.7297

Max Act: 5.4864. Min Act: -0.1700

Data Index: 747409 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 5.7297. Min Range: -5.7297

Max Act: 5.5050. Min Act: -0.1700

Data Index: 120735 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 5.7297. Min Range: -5.7297

Max Act: 5.4693. Min Act: -0.1699

Data Index: 221589 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 5.7297. Min Range: -5.7297

Max Act: 5.4795. Min Act: -0.1700

Data Index: 115452 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 5.7297. Min Range: -5.7297

Max Act: 5.4328. Min Act: -0.1699

Data Index: 1184878 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 5.7297. Min Range: -5.7297

Max Act: 5.4459. Min Act: -0.1700

Data Index: 1286913 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 5.7297. Min Range: -5.7297

Max Act: 5.4784. Min Act: -0.1700

Data Index: 79281 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 5.7297. Min Range: -5.7297

Max Act: 5.4638. Min Act: -0.1700

Data Index: 859939 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 5.7297. Min Range: -5.7297

Max Act: 5.4024. Min Act: -0.1700

Data Index: 860070 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 5.7297. Min Range: -5.7297

Max Act: 5.3778. Min Act: -0.1700

Data Index: 390068 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 5.7297. Min Range: -5.7297

Max Act: 5.4047. Min Act: -0.1700

Data Index: 481785 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 5.7297. Min Range: -5.7297

Max Act: 5.3835. Min Act: -0.1700

Data Index: 26626 (C4 (Web Text))

Max Activating Token Index: 358

Text #16

Max Range: 5.7297. Min Range: -5.7297

Max Act: 5.3842. Min Act: -0.1700

Data Index: 1000919 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 5.7297. Min Range: -5.7297

Max Act: 5.3289. Min Act: -0.1700

Data Index: 111450 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 5.7297. Min Range: -5.7297

Max Act: 5.3262. Min Act: -0.1700

Data Index: 1243827 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 5.7297. Min Range: -5.7297

Max Act: 5.3262. Min Act: -0.1700

Data Index: 258822 (C4 (Web Text))

Max Activating Token Index: 705