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

Dataset: Open Web Text

Neuron 2318 in Layer 4

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: 3.6806. Min Range: -3.6806

Max Act: 3.6806. Min Act: -0.1700

Data Index: 1696320 (Open Web Text)

Max Activating Token Index: 200

Text #1

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.4818. Min Act: -0.1700

Data Index: 7110359 (Open Web Text)

Max Activating Token Index: 460

Text #2

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.4707. Min Act: -0.1700

Data Index: 2412385 (Open Web Text)

Max Activating Token Index: 990

Text #3

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.4714. Min Act: -0.1700

Data Index: 4113453 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.4508. Min Act: -0.1700

Data Index: 3638933 (Open Web Text)

Max Activating Token Index: 1016

Text #5

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.4032. Min Act: -0.1700

Data Index: 1650100 (Open Web Text)

Max Activating Token Index: 679

Text #6

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.4186. Min Act: -0.1700

Data Index: 1613035 (Open Web Text)

Max Activating Token Index: 890

Text #7

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.4553. Min Act: -0.1700

Data Index: 3939613 (Open Web Text)

Max Activating Token Index: 971

Text #8

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.4069. Min Act: -0.1700

Data Index: 6400859 (Open Web Text)

Max Activating Token Index: 670

Text #9

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.3856. Min Act: -0.1700

Data Index: 8409651 (Open Web Text)

Max Activating Token Index: 140

Text #10

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.4194. Min Act: -0.1700

Data Index: 2573935 (Open Web Text)

Max Activating Token Index: 382

Text #11

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.3765. Min Act: -0.1700

Data Index: 5971323 (Open Web Text)

Max Activating Token Index: 511

Text #12

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.3694. Min Act: -0.1700

Data Index: 6478023 (Open Web Text)

Max Activating Token Index: 999

Text #13

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.3730. Min Act: -0.1700

Data Index: 6251983 (Open Web Text)

Max Activating Token Index: 267

Text #14

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.3644. Min Act: -0.1700

Data Index: 1954060 (Open Web Text)

Max Activating Token Index: 194

Text #15

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.3528. Min Act: -0.1700

Data Index: 594578 (Open Web Text)

Max Activating Token Index: 924

Text #16

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.3208. Min Act: -0.1700

Data Index: 4113396 (Open Web Text)

Max Activating Token Index: 968

Text #17

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.3460. Min Act: -0.1700

Data Index: 6671446 (Open Web Text)

Max Activating Token Index: 975

Text #18

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.3365. Min Act: -0.1700

Data Index: 944629 (Open Web Text)

Max Activating Token Index: 85

Text #19

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.3252. Min Act: -0.1700

Data Index: 6414210 (Open Web Text)

Max Activating Token Index: 555