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

Dataset: Open Web Text

Neuron 869 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: 1.2760. Min Range: -1.2760

Max Act: 1.2760. Min Act: -0.1682

Data Index: 644809 (Open Web Text)

Max Activating Token Index: 22

Text #1

Max Range: 1.2760. Min Range: -1.2760

Max Act: 1.2712. Min Act: -0.1694

Data Index: 5998002 (Open Web Text)

Max Activating Token Index: 17

Text #2

Max Range: 1.2760. Min Range: -1.2760

Max Act: 1.2653. Min Act: -0.1700

Data Index: 253759 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 1.2760. Min Range: -1.2760

Max Act: 1.2628. Min Act: -0.1700

Data Index: 8033989 (Open Web Text)

Max Activating Token Index: 19

Text #4

Max Range: 1.2760. Min Range: -1.2760

Max Act: 1.2604. Min Act: -0.1673

Data Index: 7534360 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 1.2760. Min Range: -1.2760

Max Act: 1.2475. Min Act: -0.1699

Data Index: 819650 (Open Web Text)

Max Activating Token Index: 11

Text #6

Max Range: 1.2760. Min Range: -1.2760

Max Act: 1.2432. Min Act: -0.1687

Data Index: 4341667 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 1.2760. Min Range: -1.2760

Max Act: 1.2401. Min Act: -0.1700

Data Index: 2629459 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 1.2760. Min Range: -1.2760

Max Act: 1.2376. Min Act: -0.1697

Data Index: 1949901 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 1.2760. Min Range: -1.2760

Max Act: 1.2298. Min Act: -0.1664

Data Index: 5739035 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 1.2760. Min Range: -1.2760

Max Act: 1.2299. Min Act: -0.1698

Data Index: 7537342 (Open Web Text)

Max Activating Token Index: 12

Text #11

Max Range: 1.2760. Min Range: -1.2760

Max Act: 1.2278. Min Act: -0.1685

Data Index: 5201796 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 1.2760. Min Range: -1.2760

Max Act: 1.2395. Min Act: -0.1616

Data Index: 6800561 (Open Web Text)

Max Activating Token Index: 84

Text #13

Max Range: 1.2760. Min Range: -1.2760

Max Act: 1.2334. Min Act: -0.1700

Data Index: 1129275 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 1.2760. Min Range: -1.2760

Max Act: 1.2327. Min Act: -0.1694

Data Index: 4940373 (Open Web Text)

Max Activating Token Index: 11

Text #15

Max Range: 1.2760. Min Range: -1.2760

Max Act: 1.2262. Min Act: -0.1699

Data Index: 6506351 (Open Web Text)

Max Activating Token Index: 28

Text #16

Max Range: 1.2760. Min Range: -1.2760

Max Act: 1.2295. Min Act: -0.1673

Data Index: 5259499 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 1.2760. Min Range: -1.2760

Max Act: 1.2061. Min Act: -0.1697

Data Index: 3596331 (Open Web Text)

Max Activating Token Index: 17

Text #18

Max Range: 1.2760. Min Range: -1.2760

Max Act: 1.2207. Min Act: -0.1700

Data Index: 3443235 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 1.2760. Min Range: -1.2760

Max Act: 1.2197. Min Act: -0.1700

Data Index: 4940374 (Open Web Text)

Max Activating Token Index: 7