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

Dataset: Open Web Text

Neuron 692 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: 3.0910. Min Range: -3.0910

Max Act: 3.0910. Min Act: -0.1700

Data Index: 48283 (Open Web Text)

Max Activating Token Index: 661

Text #1

Max Range: 3.0910. Min Range: -3.0910

Max Act: 3.0049. Min Act: -0.1700

Data Index: 5924115 (Open Web Text)

Max Activating Token Index: 310

Text #2

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.9832. Min Act: -0.1700

Data Index: 7680727 (Open Web Text)

Max Activating Token Index: 828

Text #3

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.9319. Min Act: -0.1700

Data Index: 1706117 (Open Web Text)

Max Activating Token Index: 340

Text #4

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.9350. Min Act: -0.1700

Data Index: 8382243 (Open Web Text)

Max Activating Token Index: 746

Text #5

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.9375. Min Act: -0.1700

Data Index: 3757872 (Open Web Text)

Max Activating Token Index: 936

Text #6

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.9056. Min Act: -0.1700

Data Index: 3865667 (Open Web Text)

Max Activating Token Index: 679

Text #7

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.9147. Min Act: -0.1700

Data Index: 8387882 (Open Web Text)

Max Activating Token Index: 298

Text #8

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.9067. Min Act: -0.1700

Data Index: 157076 (Open Web Text)

Max Activating Token Index: 552

Text #9

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.9194. Min Act: -0.1700

Data Index: 1074834 (Open Web Text)

Max Activating Token Index: 687

Text #10

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.8932. Min Act: -0.1700

Data Index: 5046808 (Open Web Text)

Max Activating Token Index: 771

Text #11

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.9158. Min Act: -0.1700

Data Index: 8320434 (Open Web Text)

Max Activating Token Index: 257

Text #12

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.9001. Min Act: -0.1700

Data Index: 2034155 (Open Web Text)

Max Activating Token Index: 832

Text #13

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.9044. Min Act: -0.1700

Data Index: 5030543 (Open Web Text)

Max Activating Token Index: 742

Text #14

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.9137. Min Act: -0.1700

Data Index: 4848424 (Open Web Text)

Max Activating Token Index: 377

Text #15

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.9130. Min Act: -0.1700

Data Index: 5233062 (Open Web Text)

Max Activating Token Index: 745

Text #16

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.8967. Min Act: -0.1700

Data Index: 4027026 (Open Web Text)

Max Activating Token Index: 372

Text #17

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.8855. Min Act: -0.1700

Data Index: 7689919 (Open Web Text)

Max Activating Token Index: 776

Text #18

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.8575. Min Act: -0.1700

Data Index: 7677612 (Open Web Text)

Max Activating Token Index: 1011

Text #19

Max Range: 3.0910. Min Range: -3.0910

Max Act: 2.8470. Min Act: -0.1700

Data Index: 3057112 (Open Web Text)

Max Activating Token Index: 951