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

Dataset: Open Web Text

Neuron 419 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: 4.0810. Min Range: -4.0810

Max Act: 4.0810. Min Act: -0.1700

Data Index: 2447629 (Open Web Text)

Max Activating Token Index: 672

Text #1

Max Range: 4.0810. Min Range: -4.0810

Max Act: 4.0223. Min Act: -0.1700

Data Index: 6937378 (Open Web Text)

Max Activating Token Index: 643

Text #2

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.9706. Min Act: -0.1700

Data Index: 6875476 (Open Web Text)

Max Activating Token Index: 689

Text #3

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.9428. Min Act: -0.1700

Data Index: 4595119 (Open Web Text)

Max Activating Token Index: 364

Text #4

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.9060. Min Act: -0.1700

Data Index: 3408984 (Open Web Text)

Max Activating Token Index: 683

Text #5

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.9421. Min Act: -0.1700

Data Index: 3063228 (Open Web Text)

Max Activating Token Index: 786

Text #6

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.9313. Min Act: -0.1700

Data Index: 8118651 (Open Web Text)

Max Activating Token Index: 286

Text #7

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.8763. Min Act: -0.1700

Data Index: 2519256 (Open Web Text)

Max Activating Token Index: 681

Text #8

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.8065. Min Act: -0.1700

Data Index: 7088430 (Open Web Text)

Max Activating Token Index: 764

Text #9

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.7905. Min Act: -0.1700

Data Index: 4785077 (Open Web Text)

Max Activating Token Index: 672

Text #10

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.7401. Min Act: -0.1700

Data Index: 2703125 (Open Web Text)

Max Activating Token Index: 828

Text #11

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.7434. Min Act: -0.1700

Data Index: 5692799 (Open Web Text)

Max Activating Token Index: 453

Text #12

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.7699. Min Act: -0.1700

Data Index: 2023776 (Open Web Text)

Max Activating Token Index: 125

Text #13

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.7380. Min Act: -0.1700

Data Index: 6652111 (Open Web Text)

Max Activating Token Index: 232

Text #14

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.6886. Min Act: -0.1700

Data Index: 1806787 (Open Web Text)

Max Activating Token Index: 476

Text #15

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.6821. Min Act: -0.1700

Data Index: 5839427 (Open Web Text)

Max Activating Token Index: 926

Text #16

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.6667. Min Act: -0.1700

Data Index: 8273293 (Open Web Text)

Max Activating Token Index: 565

Text #17

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.7008. Min Act: -0.1700

Data Index: 1655878 (Open Web Text)

Max Activating Token Index: 504

Text #18

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.6774. Min Act: -0.1700

Data Index: 5001970 (Open Web Text)

Max Activating Token Index: 527

Text #19

Max Range: 4.0810. Min Range: -4.0810

Max Act: 3.6495. Min Act: -0.1700

Data Index: 105680 (Open Web Text)

Max Activating Token Index: 739