Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 436 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.5590. Min Range: -3.5590

Max Act: 3.5590. Min Act: -0.1688

Data Index: 1353267 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 3.5590. Min Range: -3.5590

Max Act: 3.4336. Min Act: -0.1700

Data Index: 1340283 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 3.5590. Min Range: -3.5590

Max Act: 3.3395. Min Act: -0.1700

Data Index: 1284969 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 3.5590. Min Range: -3.5590

Max Act: 3.3238. Min Act: -0.1700

Data Index: 1112353 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 3.5590. Min Range: -3.5590

Max Act: 3.3238. Min Act: -0.1700

Data Index: 479290 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 3.5590. Min Range: -3.5590

Max Act: 3.3081. Min Act: -0.1700

Data Index: 1067898 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 3.5590. Min Range: -3.5590

Max Act: 3.2924. Min Act: -0.1700

Data Index: 112464 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 3.5590. Min Range: -3.5590

Max Act: 3.2767. Min Act: -0.1700

Data Index: 925682 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 3.5590. Min Range: -3.5590

Max Act: 3.2767. Min Act: -0.1700

Data Index: 1060525 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 3.5590. Min Range: -3.5590

Max Act: 3.2924. Min Act: -0.1699

Data Index: 446762 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 3.5590. Min Range: -3.5590

Max Act: 3.2610. Min Act: -0.1700

Data Index: 231865 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 3.5590. Min Range: -3.5590

Max Act: 3.2453. Min Act: -0.1700

Data Index: 1310884 (C4 (Web Text))

Max Activating Token Index: 525

Text #12

Max Range: 3.5590. Min Range: -3.5590

Max Act: 3.2767. Min Act: -0.1700

Data Index: 303258 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 3.5590. Min Range: -3.5590

Max Act: 3.2610. Min Act: -0.1700

Data Index: 393064 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 3.5590. Min Range: -3.5590

Max Act: 3.2610. Min Act: -0.1700

Data Index: 904150 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 3.5590. Min Range: -3.5590

Max Act: 3.2295. Min Act: -0.1700

Data Index: 235916 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 3.5590. Min Range: -3.5590

Max Act: 3.2453. Min Act: -0.1700

Data Index: 65129 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 3.5590. Min Range: -3.5590

Max Act: 3.2610. Min Act: -0.1700

Data Index: 453263 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 3.5590. Min Range: -3.5590

Max Act: 3.2610. Min Act: -0.1700

Data Index: 595483 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 3.5590. Min Range: -3.5590

Max Act: 3.1981. Min Act: -0.1700

Data Index: 1053537 (C4 (Web Text))

Max Activating Token Index: 426