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

Dataset: Open Web Text

Neuron 197 in Layer 3

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: 3.8772. Min Range: -3.8772

Max Act: 3.8772. Min Act: -0.1700

Data Index: 6748681 (Open Web Text)

Max Activating Token Index: 621

Text #1

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.7577. Min Act: -0.1700

Data Index: 1928231 (Open Web Text)

Max Activating Token Index: 596

Text #2

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.6554. Min Act: -0.1700

Data Index: 4434479 (Open Web Text)

Max Activating Token Index: 283

Text #3

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.6206. Min Act: -0.1700

Data Index: 5464569 (Open Web Text)

Max Activating Token Index: 506

Text #4

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.6253. Min Act: -0.1700

Data Index: 7294875 (Open Web Text)

Max Activating Token Index: 471

Text #5

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.6228. Min Act: -0.1700

Data Index: 4686451 (Open Web Text)

Max Activating Token Index: 30

Text #6

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.6259. Min Act: -0.1700

Data Index: 1169172 (Open Web Text)

Max Activating Token Index: 464

Text #7

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.6004. Min Act: -0.1700

Data Index: 499141 (Open Web Text)

Max Activating Token Index: 1014

Text #8

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.5667. Min Act: -0.1700

Data Index: 2045643 (Open Web Text)

Max Activating Token Index: 390

Text #9

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.5284. Min Act: -0.1700

Data Index: 6813598 (Open Web Text)

Max Activating Token Index: 590

Text #10

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.4921. Min Act: -0.1700

Data Index: 2495754 (Open Web Text)

Max Activating Token Index: 1019

Text #11

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.4990. Min Act: -0.1700

Data Index: 1721150 (Open Web Text)

Max Activating Token Index: 617

Text #12

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.5184. Min Act: -0.1700

Data Index: 6798587 (Open Web Text)

Max Activating Token Index: 89

Text #13

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.4928. Min Act: -0.1700

Data Index: 1764287 (Open Web Text)

Max Activating Token Index: 386

Text #14

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.4950. Min Act: -0.1700

Data Index: 6224726 (Open Web Text)

Max Activating Token Index: 944

Text #15

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.4952. Min Act: -0.1700

Data Index: 6642369 (Open Web Text)

Max Activating Token Index: 154

Text #16

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.4785. Min Act: -0.1700

Data Index: 5927722 (Open Web Text)

Max Activating Token Index: 801

Text #17

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.4860. Min Act: -0.1700

Data Index: 1606729 (Open Web Text)

Max Activating Token Index: 66

Text #18

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.4716. Min Act: -0.1700

Data Index: 2322085 (Open Web Text)

Max Activating Token Index: 372

Text #19

Max Range: 3.8772. Min Range: -3.8772

Max Act: 3.4675. Min Act: -0.1700

Data Index: 8053605 (Open Web Text)

Max Activating Token Index: 462