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

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

Neuron 1695 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: 4.3692. Min Range: -4.3692

Max Act: 4.3692. Min Act: -0.1700

Data Index: 352161 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 4.3692. Min Range: -4.3692

Max Act: 4.2886. Min Act: -0.1700

Data Index: 546650 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 4.3692. Min Range: -4.3692

Max Act: 4.3461. Min Act: -0.1700

Data Index: 327245 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 4.3692. Min Range: -4.3692

Max Act: 4.2937. Min Act: -0.1700

Data Index: 169596 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 4.3692. Min Range: -4.3692

Max Act: 4.2960. Min Act: -0.1700

Data Index: 516594 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 4.3692. Min Range: -4.3692

Max Act: 4.3227. Min Act: -0.1700

Data Index: 1054273 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 4.3692. Min Range: -4.3692

Max Act: 4.2707. Min Act: -0.1700

Data Index: 653285 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 4.3692. Min Range: -4.3692

Max Act: 4.2783. Min Act: -0.1700

Data Index: 188904 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 4.3692. Min Range: -4.3692

Max Act: 4.2136. Min Act: -0.1700

Data Index: 260007 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 4.3692. Min Range: -4.3692

Max Act: 4.1897. Min Act: -0.1700

Data Index: 888821 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 4.3692. Min Range: -4.3692

Max Act: 4.2044. Min Act: -0.1700

Data Index: 1083449 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 4.3692. Min Range: -4.3692

Max Act: 4.2049. Min Act: -0.1700

Data Index: 1318197 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 4.3692. Min Range: -4.3692

Max Act: 4.1922. Min Act: -0.1700

Data Index: 1162828 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 4.3692. Min Range: -4.3692

Max Act: 4.1320. Min Act: -0.1700

Data Index: 123787 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 4.3692. Min Range: -4.3692

Max Act: 4.1605. Min Act: -0.1700

Data Index: 590406 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 4.3692. Min Range: -4.3692

Max Act: 4.1792. Min Act: -0.1700

Data Index: 1346491 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 4.3692. Min Range: -4.3692

Max Act: 4.1963. Min Act: -0.1700

Data Index: 1021991 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 4.3692. Min Range: -4.3692

Max Act: 4.1611. Min Act: -0.1700

Data Index: 971747 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 4.3692. Min Range: -4.3692

Max Act: 4.1454. Min Act: -0.1700

Data Index: 701650 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 4.3692. Min Range: -4.3692

Max Act: 4.1649. Min Act: -0.1700

Data Index: 496821 (C4 (Web Text))

Max Activating Token Index: 577