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

Dataset: Open Web Text

Neuron 292 in Layer 5

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: 5.4500. Min Range: -5.4500

Max Act: 5.4500. Min Act: -0.1700

Data Index: 4596666 (Open Web Text)

Max Activating Token Index: 474

Text #1

Max Range: 5.4500. Min Range: -5.4500

Max Act: 5.4127. Min Act: -0.1700

Data Index: 3933177 (Open Web Text)

Max Activating Token Index: 507

Text #2

Max Range: 5.4500. Min Range: -5.4500

Max Act: 5.3828. Min Act: -0.1700

Data Index: 8797597 (Open Web Text)

Max Activating Token Index: 255

Text #3

Max Range: 5.4500. Min Range: -5.4500

Max Act: 5.4113. Min Act: -0.1700

Data Index: 8066449 (Open Web Text)

Max Activating Token Index: 941

Text #4

Max Range: 5.4500. Min Range: -5.4500

Max Act: 5.3653. Min Act: -0.1700

Data Index: 5269644 (Open Web Text)

Max Activating Token Index: 625

Text #5

Max Range: 5.4500. Min Range: -5.4500

Max Act: 5.3625. Min Act: -0.1700

Data Index: 3334048 (Open Web Text)

Max Activating Token Index: 582

Text #6

Max Range: 5.4500. Min Range: -5.4500

Max Act: 5.3597. Min Act: -0.1700

Data Index: 7852153 (Open Web Text)

Max Activating Token Index: 532

Text #7

Max Range: 5.4500. Min Range: -5.4500

Max Act: 5.3126. Min Act: -0.1700

Data Index: 2675851 (Open Web Text)

Max Activating Token Index: 904

Text #8

Max Range: 5.4500. Min Range: -5.4500

Max Act: 5.3541. Min Act: -0.1700

Data Index: 2876812 (Open Web Text)

Max Activating Token Index: 828

Text #9

Max Range: 5.4500. Min Range: -5.4500

Max Act: 5.3099. Min Act: -0.1700

Data Index: 2834172 (Open Web Text)

Max Activating Token Index: 628

Text #10

Max Range: 5.4500. Min Range: -5.4500

Max Act: 5.3351. Min Act: -0.1700

Data Index: 1835534 (Open Web Text)

Max Activating Token Index: 555

Text #11

Max Range: 5.4500. Min Range: -5.4500

Max Act: 5.3309. Min Act: -0.1700

Data Index: 8770551 (Open Web Text)

Max Activating Token Index: 998

Text #12

Max Range: 5.4500. Min Range: -5.4500

Max Act: 5.3502. Min Act: -0.1700

Data Index: 4242783 (Open Web Text)

Max Activating Token Index: 161

Text #13

Max Range: 5.4500. Min Range: -5.4500

Max Act: 5.3421. Min Act: -0.1700

Data Index: 8034268 (Open Web Text)

Max Activating Token Index: 805

Text #14

Max Range: 5.4500. Min Range: -5.4500

Max Act: 5.3533. Min Act: -0.1700

Data Index: 7894990 (Open Web Text)

Max Activating Token Index: 492

Text #15

Max Range: 5.4500. Min Range: -5.4500

Max Act: 5.3316. Min Act: -0.1700

Data Index: 6941814 (Open Web Text)

Max Activating Token Index: 847

Text #16

Max Range: 5.4500. Min Range: -5.4500

Max Act: 5.3146. Min Act: -0.1700

Data Index: 6895936 (Open Web Text)

Max Activating Token Index: 237

Text #17

Max Range: 5.4500. Min Range: -5.4500

Max Act: 5.2635. Min Act: -0.1700

Data Index: 653520 (Open Web Text)

Max Activating Token Index: 218

Text #18

Max Range: 5.4500. Min Range: -5.4500

Max Act: 5.3340. Min Act: -0.1700

Data Index: 2805928 (Open Web Text)

Max Activating Token Index: 966

Text #19

Max Range: 5.4500. Min Range: -5.4500

Max Act: 5.3173. Min Act: -0.1700

Data Index: 4896576 (Open Web Text)

Max Activating Token Index: 432