Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1486 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.4103. Min Range: -3.4103

Max Act: 3.4103. Min Act: -0.1700

Data Index: 676842 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 3.4103. Min Range: -3.4103

Max Act: 3.3475. Min Act: -0.1700

Data Index: 680335 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 3.4103. Min Range: -3.4103

Max Act: 3.3162. Min Act: -0.1700

Data Index: 292344 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 3.4103. Min Range: -3.4103

Max Act: 3.3475. Min Act: -0.1700

Data Index: 558648 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 3.4103. Min Range: -3.4103

Max Act: 3.2847. Min Act: -0.1700

Data Index: 920722 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 3.4103. Min Range: -3.4103

Max Act: 3.2690. Min Act: -0.1700

Data Index: 825899 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 3.4103. Min Range: -3.4103

Max Act: 3.2533. Min Act: -0.1700

Data Index: 527322 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 3.4103. Min Range: -3.4103

Max Act: 3.2533. Min Act: -0.1700

Data Index: 1143640 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 3.4103. Min Range: -3.4103

Max Act: 3.2376. Min Act: -0.1700

Data Index: 1158031 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 3.4103. Min Range: -3.4103

Max Act: 3.2376. Min Act: -0.1700

Data Index: 233060 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 3.4103. Min Range: -3.4103

Max Act: 3.2376. Min Act: -0.1700

Data Index: 1231179 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 3.4103. Min Range: -3.4103

Max Act: 3.2376. Min Act: -0.1700

Data Index: 664985 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 3.4103. Min Range: -3.4103

Max Act: 3.1904. Min Act: -0.1700

Data Index: 414604 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 3.4103. Min Range: -3.4103

Max Act: 3.2376. Min Act: -0.1700

Data Index: 61500 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 3.4103. Min Range: -3.4103

Max Act: 3.2219. Min Act: -0.1700

Data Index: 425711 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 3.4103. Min Range: -3.4103

Max Act: 3.1904. Min Act: -0.1700

Data Index: 1358928 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 3.4103. Min Range: -3.4103

Max Act: 3.1904. Min Act: -0.1700

Data Index: 947252 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 3.4103. Min Range: -3.4103

Max Act: 3.2061. Min Act: -0.1700

Data Index: 465821 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 3.4103. Min Range: -3.4103

Max Act: 3.2219. Min Act: -0.1700

Data Index: 368441 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 3.4103. Min Range: -3.4103

Max Act: 3.2219. Min Act: -0.1700

Data Index: 389335 (C4 (Web Text))

Max Activating Token Index: 416