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

Dataset: Open Web Text

Neuron 888 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: 3.8625. Min Range: -3.8625

Max Act: 3.8625. Min Act: -0.1700

Data Index: 4439491 (Open Web Text)

Max Activating Token Index: 614

Text #1

Max Range: 3.8625. Min Range: -3.8625

Max Act: 3.6420. Min Act: -0.1700

Data Index: 3823967 (Open Web Text)

Max Activating Token Index: 941

Text #2

Max Range: 3.8625. Min Range: -3.8625

Max Act: 3.5809. Min Act: -0.1700

Data Index: 1250043 (Open Web Text)

Max Activating Token Index: 656

Text #3

Max Range: 3.8625. Min Range: -3.8625

Max Act: 3.5561. Min Act: -0.1700

Data Index: 3790576 (Open Web Text)

Max Activating Token Index: 952

Text #4

Max Range: 3.8625. Min Range: -3.8625

Max Act: 3.5431. Min Act: -0.1700

Data Index: 7815257 (Open Web Text)

Max Activating Token Index: 1022

Text #5

Max Range: 3.8625. Min Range: -3.8625

Max Act: 3.5312. Min Act: -0.1700

Data Index: 7952094 (Open Web Text)

Max Activating Token Index: 835

Text #6

Max Range: 3.8625. Min Range: -3.8625

Max Act: 3.5342. Min Act: -0.1700

Data Index: 8543312 (Open Web Text)

Max Activating Token Index: 971

Text #7

Max Range: 3.8625. Min Range: -3.8625

Max Act: 3.5060. Min Act: -0.1700

Data Index: 3994657 (Open Web Text)

Max Activating Token Index: 585

Text #8

Max Range: 3.8625. Min Range: -3.8625

Max Act: 3.5077. Min Act: -0.1700

Data Index: 7667874 (Open Web Text)

Max Activating Token Index: 864

Text #9

Max Range: 3.8625. Min Range: -3.8625

Max Act: 3.4956. Min Act: -0.1700

Data Index: 5756902 (Open Web Text)

Max Activating Token Index: 295

Text #10

Max Range: 3.8625. Min Range: -3.8625

Max Act: 3.4891. Min Act: -0.1700

Data Index: 2335178 (Open Web Text)

Max Activating Token Index: 975

Text #11

Max Range: 3.8625. Min Range: -3.8625

Max Act: 3.4876. Min Act: -0.1700

Data Index: 1847589 (Open Web Text)

Max Activating Token Index: 892

Text #12

Max Range: 3.8625. Min Range: -3.8625

Max Act: 3.4869. Min Act: -0.1700

Data Index: 4782467 (Open Web Text)

Max Activating Token Index: 892

Text #13

Max Range: 3.8625. Min Range: -3.8625

Max Act: 3.4706. Min Act: -0.1700

Data Index: 4697829 (Open Web Text)

Max Activating Token Index: 1000

Text #14

Max Range: 3.8625. Min Range: -3.8625

Max Act: 3.4636. Min Act: -0.1700

Data Index: 2101171 (Open Web Text)

Max Activating Token Index: 852

Text #15

Max Range: 3.8625. Min Range: -3.8625

Max Act: 3.4374. Min Act: -0.1700

Data Index: 4790468 (Open Web Text)

Max Activating Token Index: 820

Text #16

Max Range: 3.8625. Min Range: -3.8625

Max Act: 3.4589. Min Act: -0.1700

Data Index: 8694924 (Open Web Text)

Max Activating Token Index: 968

Text #17

Max Range: 3.8625. Min Range: -3.8625

Max Act: 3.4260. Min Act: -0.1700

Data Index: 572916 (Open Web Text)

Max Activating Token Index: 574

Text #18

Max Range: 3.8625. Min Range: -3.8625

Max Act: 3.4328. Min Act: -0.1700

Data Index: 7050948 (Open Web Text)

Max Activating Token Index: 1009

Text #19

Max Range: 3.8625. Min Range: -3.8625

Max Act: 3.4518. Min Act: -0.1700

Data Index: 7623747 (Open Web Text)

Max Activating Token Index: 728