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

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

Neuron 494 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: 4.4968. Min Range: -4.4968

Max Act: 4.4968. Min Act: -0.1700

Data Index: 292488 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 4.4968. Min Range: -4.4968

Max Act: 4.4563. Min Act: -0.1700

Data Index: 1120570 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 4.4968. Min Range: -4.4968

Max Act: 4.4073. Min Act: -0.1700

Data Index: 1342682 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 4.4968. Min Range: -4.4968

Max Act: 4.3468. Min Act: -0.1700

Data Index: 1403972 (Python Code)

Max Activating Token Index: 494

Text #4

Max Range: 4.4968. Min Range: -4.4968

Max Act: 4.3162. Min Act: -0.1700

Data Index: 922313 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 4.4968. Min Range: -4.4968

Max Act: 4.2318. Min Act: -0.1700

Data Index: 648880 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 4.4968. Min Range: -4.4968

Max Act: 4.2059. Min Act: -0.1700

Data Index: 1597971 (Python Code)

Max Activating Token Index: 619

Text #7

Max Range: 4.4968. Min Range: -4.4968

Max Act: 4.1651. Min Act: -0.1700

Data Index: 1064882 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 4.4968. Min Range: -4.4968

Max Act: 4.1638. Min Act: -0.1700

Data Index: 1431647 (Python Code)

Max Activating Token Index: 166

Text #9

Max Range: 4.4968. Min Range: -4.4968

Max Act: 4.1574. Min Act: -0.1700

Data Index: 486265 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 4.4968. Min Range: -4.4968

Max Act: 4.1565. Min Act: -0.1694

Data Index: 1476791 (Python Code)

Max Activating Token Index: 831

Text #11

Max Range: 4.4968. Min Range: -4.4968

Max Act: 4.1364. Min Act: -0.1700

Data Index: 1210431 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 4.4968. Min Range: -4.4968

Max Act: 4.1284. Min Act: -0.1700

Data Index: 181291 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 4.4968. Min Range: -4.4968

Max Act: 4.1114. Min Act: -0.1700

Data Index: 424798 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 4.4968. Min Range: -4.4968

Max Act: 4.1321. Min Act: -0.1700

Data Index: 1305056 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 4.4968. Min Range: -4.4968

Max Act: 4.1005. Min Act: -0.1699

Data Index: 1440174 (Python Code)

Max Activating Token Index: 849

Text #16

Max Range: 4.4968. Min Range: -4.4968

Max Act: 4.0732. Min Act: -0.1700

Data Index: 272592 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 4.4968. Min Range: -4.4968

Max Act: 4.0885. Min Act: -0.1699

Data Index: 935464 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 4.4968. Min Range: -4.4968

Max Act: 4.0906. Min Act: -0.1700

Data Index: 223605 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 4.4968. Min Range: -4.4968

Max Act: 4.0407. Min Act: -0.1700

Data Index: 889547 (C4 (Web Text))

Max Activating Token Index: 618