Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2036 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.2717. Min Range: -4.2717

Max Act: 4.2717. Min Act: -0.1700

Data Index: 7593600 (Open Web Text)

Max Activating Token Index: 989

Text #1

Max Range: 4.2717. Min Range: -4.2717

Max Act: 4.2495. Min Act: -0.1700

Data Index: 2986102 (Open Web Text)

Max Activating Token Index: 562

Text #2

Max Range: 4.2717. Min Range: -4.2717

Max Act: 4.2519. Min Act: -0.1700

Data Index: 3098407 (Open Web Text)

Max Activating Token Index: 35

Text #3

Max Range: 4.2717. Min Range: -4.2717

Max Act: 4.2250. Min Act: -0.1700

Data Index: 3205613 (Open Web Text)

Max Activating Token Index: 31

Text #4

Max Range: 4.2717. Min Range: -4.2717

Max Act: 4.2586. Min Act: -0.1700

Data Index: 7097003 (Open Web Text)

Max Activating Token Index: 858

Text #5

Max Range: 4.2717. Min Range: -4.2717

Max Act: 4.2206. Min Act: -0.1700

Data Index: 2134312 (Open Web Text)

Max Activating Token Index: 1008

Text #6

Max Range: 4.2717. Min Range: -4.2717

Max Act: 4.2084. Min Act: -0.1700

Data Index: 3627351 (Open Web Text)

Max Activating Token Index: 1007

Text #7

Max Range: 4.2717. Min Range: -4.2717

Max Act: 4.2157. Min Act: -0.1700

Data Index: 2276805 (Open Web Text)

Max Activating Token Index: 752

Text #8

Max Range: 4.2717. Min Range: -4.2717

Max Act: 4.2019. Min Act: -0.1700

Data Index: 6372965 (Open Web Text)

Max Activating Token Index: 497

Text #9

Max Range: 4.2717. Min Range: -4.2717

Max Act: 4.2010. Min Act: -0.1700

Data Index: 3205610 (Open Web Text)

Max Activating Token Index: 1012

Text #10

Max Range: 4.2717. Min Range: -4.2717

Max Act: 4.1811. Min Act: -0.1700

Data Index: 3205609 (Open Web Text)

Max Activating Token Index: 992

Text #11

Max Range: 4.2717. Min Range: -4.2717

Max Act: 4.1858. Min Act: -0.1700

Data Index: 6627900 (Open Web Text)

Max Activating Token Index: 500

Text #12

Max Range: 4.2717. Min Range: -4.2717

Max Act: 4.2014. Min Act: -0.1700

Data Index: 7950114 (Open Web Text)

Max Activating Token Index: 554

Text #13

Max Range: 4.2717. Min Range: -4.2717

Max Act: 4.1811. Min Act: -0.1700

Data Index: 4328612 (Open Web Text)

Max Activating Token Index: 1022

Text #14

Max Range: 4.2717. Min Range: -4.2717

Max Act: 4.1599. Min Act: -0.1700

Data Index: 442227 (Open Web Text)

Max Activating Token Index: 336

Text #15

Max Range: 4.2717. Min Range: -4.2717

Max Act: 4.1609. Min Act: -0.1700

Data Index: 3205608 (Open Web Text)

Max Activating Token Index: 972

Text #16

Max Range: 4.2717. Min Range: -4.2717

Max Act: 4.1729. Min Act: -0.1700

Data Index: 6292630 (Open Web Text)

Max Activating Token Index: 470

Text #17

Max Range: 4.2717. Min Range: -4.2717

Max Act: 4.1242. Min Act: -0.1700

Data Index: 3326071 (Open Web Text)

Max Activating Token Index: 493

Text #18

Max Range: 4.2717. Min Range: -4.2717

Max Act: 4.1396. Min Act: -0.1700

Data Index: 2870001 (Open Web Text)

Max Activating Token Index: 233

Text #19

Max Range: 4.2717. Min Range: -4.2717

Max Act: 4.1382. Min Act: -0.1700

Data Index: 3205599 (Open Web Text)

Max Activating Token Index: 788