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

Dataset: Open Web Text

Neuron 1818 in Layer 6

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: 3.2924. Min Range: -3.2924

Max Act: 3.2924. Min Act: -0.1700

Data Index: 1915771 (Open Web Text)

Max Activating Token Index: 288

Text #1

Max Range: 3.2924. Min Range: -3.2924

Max Act: 3.2780. Min Act: -0.1700

Data Index: 1202679 (Open Web Text)

Max Activating Token Index: 703

Text #2

Max Range: 3.2924. Min Range: -3.2924

Max Act: 3.2575. Min Act: -0.1700

Data Index: 4983719 (Open Web Text)

Max Activating Token Index: 500

Text #3

Max Range: 3.2924. Min Range: -3.2924

Max Act: 3.2477. Min Act: -0.1700

Data Index: 2846007 (Open Web Text)

Max Activating Token Index: 212

Text #4

Max Range: 3.2924. Min Range: -3.2924

Max Act: 3.2355. Min Act: -0.1700

Data Index: 3681916 (Open Web Text)

Max Activating Token Index: 633

Text #5

Max Range: 3.2924. Min Range: -3.2924

Max Act: 3.2404. Min Act: -0.1700

Data Index: 1049275 (Open Web Text)

Max Activating Token Index: 794

Text #6

Max Range: 3.2924. Min Range: -3.2924

Max Act: 3.2482. Min Act: -0.1700

Data Index: 5807864 (Open Web Text)

Max Activating Token Index: 638

Text #7

Max Range: 3.2924. Min Range: -3.2924

Max Act: 3.2161. Min Act: -0.1700

Data Index: 3141093 (Open Web Text)

Max Activating Token Index: 87

Text #8

Max Range: 3.2924. Min Range: -3.2924

Max Act: 3.1989. Min Act: -0.1700

Data Index: 7366746 (Open Web Text)

Max Activating Token Index: 382

Text #9

Max Range: 3.2924. Min Range: -3.2924

Max Act: 3.2066. Min Act: -0.1700

Data Index: 8562271 (Open Web Text)

Max Activating Token Index: 181

Text #10

Max Range: 3.2924. Min Range: -3.2924

Max Act: 3.1916. Min Act: -0.1700

Data Index: 2388337 (Open Web Text)

Max Activating Token Index: 355

Text #11

Max Range: 3.2924. Min Range: -3.2924

Max Act: 3.2068. Min Act: -0.1700

Data Index: 6154705 (Open Web Text)

Max Activating Token Index: 210

Text #12

Max Range: 3.2924. Min Range: -3.2924

Max Act: 3.2033. Min Act: -0.1700

Data Index: 2379089 (Open Web Text)

Max Activating Token Index: 326

Text #13

Max Range: 3.2924. Min Range: -3.2924

Max Act: 3.1766. Min Act: -0.1700

Data Index: 6037572 (Open Web Text)

Max Activating Token Index: 788

Text #14

Max Range: 3.2924. Min Range: -3.2924

Max Act: 3.1655. Min Act: -0.1700

Data Index: 2450146 (Open Web Text)

Max Activating Token Index: 134

Text #15

Max Range: 3.2924. Min Range: -3.2924

Max Act: 3.1580. Min Act: -0.1700

Data Index: 5782996 (Open Web Text)

Max Activating Token Index: 39

Text #16

Max Range: 3.2924. Min Range: -3.2924

Max Act: 3.1496. Min Act: -0.1700

Data Index: 1986955 (Open Web Text)

Max Activating Token Index: 192

Text #17

Max Range: 3.2924. Min Range: -3.2924

Max Act: 3.1536. Min Act: -0.1700

Data Index: 419874 (Open Web Text)

Max Activating Token Index: 501

Text #18

Max Range: 3.2924. Min Range: -3.2924

Max Act: 3.1592. Min Act: -0.1700

Data Index: 4340726 (Open Web Text)

Max Activating Token Index: 520

Text #19

Max Range: 3.2924. Min Range: -3.2924

Max Act: 3.1447. Min Act: -0.1700

Data Index: 7046131 (Open Web Text)

Max Activating Token Index: 283