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

Dataset: Open Web Text

Neuron 1431 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: 3.2515. Min Range: -3.2515

Max Act: 3.2412. Min Act: -0.1700

Data Index: 4137335 (Open Web Text)

Max Activating Token Index: 640

Text #1

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.2515. Min Act: -0.1700

Data Index: 6974839 (Open Web Text)

Max Activating Token Index: 341

Text #2

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.1991. Min Act: -0.1700

Data Index: 5259915 (Open Web Text)

Max Activating Token Index: 853

Text #3

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.1611. Min Act: -0.1700

Data Index: 2996962 (Open Web Text)

Max Activating Token Index: 984

Text #4

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.1868. Min Act: -0.1700

Data Index: 1111672 (Open Web Text)

Max Activating Token Index: 938

Text #5

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.1836. Min Act: -0.1700

Data Index: 8598396 (Open Web Text)

Max Activating Token Index: 639

Text #6

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.1600. Min Act: -0.1700

Data Index: 2792519 (Open Web Text)

Max Activating Token Index: 380

Text #7

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.1056. Min Act: -0.1700

Data Index: 1524481 (Open Web Text)

Max Activating Token Index: 457

Text #8

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.1444. Min Act: -0.1700

Data Index: 3912714 (Open Web Text)

Max Activating Token Index: 898

Text #9

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.1320. Min Act: -0.1700

Data Index: 795051 (Open Web Text)

Max Activating Token Index: 698

Text #10

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.1108. Min Act: -0.1700

Data Index: 5128798 (Open Web Text)

Max Activating Token Index: 918

Text #11

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.0966. Min Act: -0.1700

Data Index: 1453592 (Open Web Text)

Max Activating Token Index: 952

Text #12

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.1084. Min Act: -0.1700

Data Index: 6562171 (Open Web Text)

Max Activating Token Index: 701

Text #13

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.0792. Min Act: -0.1700

Data Index: 8351106 (Open Web Text)

Max Activating Token Index: 997

Text #14

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.1033. Min Act: -0.1700

Data Index: 338 (Open Web Text)

Max Activating Token Index: 718

Text #15

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.0892. Min Act: -0.1700

Data Index: 2613474 (Open Web Text)

Max Activating Token Index: 514

Text #16

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.1232. Min Act: -0.1700

Data Index: 5908189 (Open Web Text)

Max Activating Token Index: 668

Text #17

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.0967. Min Act: -0.1700

Data Index: 2320654 (Open Web Text)

Max Activating Token Index: 494

Text #18

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.0892. Min Act: -0.1700

Data Index: 583300 (Open Web Text)

Max Activating Token Index: 918

Text #19

Max Range: 3.2515. Min Range: -3.2515

Max Act: 3.0864. Min Act: -0.1700

Data Index: 4735299 (Open Web Text)

Max Activating Token Index: 765