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

Dataset: Open Web Text

Neuron 1041 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: 5.0118. Min Range: -5.0118

Max Act: 5.0118. Min Act: -0.1700

Data Index: 7757706 (Open Web Text)

Max Activating Token Index: 525

Text #1

Max Range: 5.0118. Min Range: -5.0118

Max Act: 4.9756. Min Act: -0.1700

Data Index: 398392 (Open Web Text)

Max Activating Token Index: 699

Text #2

Max Range: 5.0118. Min Range: -5.0118

Max Act: 4.7426. Min Act: -0.1700

Data Index: 698014 (Open Web Text)

Max Activating Token Index: 57

Text #3

Max Range: 5.0118. Min Range: -5.0118

Max Act: 4.7310. Min Act: -0.1700

Data Index: 3949018 (Open Web Text)

Max Activating Token Index: 686

Text #4

Max Range: 5.0118. Min Range: -5.0118

Max Act: 4.7143. Min Act: -0.1700

Data Index: 5601725 (Open Web Text)

Max Activating Token Index: 919

Text #5

Max Range: 5.0118. Min Range: -5.0118

Max Act: 4.6768. Min Act: -0.1700

Data Index: 4543505 (Open Web Text)

Max Activating Token Index: 275

Text #6

Max Range: 5.0118. Min Range: -5.0118

Max Act: 4.6822. Min Act: -0.1700

Data Index: 7582807 (Open Web Text)

Max Activating Token Index: 605

Text #7

Max Range: 5.0118. Min Range: -5.0118

Max Act: 4.6551. Min Act: -0.1700

Data Index: 3895220 (Open Web Text)

Max Activating Token Index: 1013

Text #8

Max Range: 5.0118. Min Range: -5.0118

Max Act: 4.6359. Min Act: -0.1700

Data Index: 6324930 (Open Web Text)

Max Activating Token Index: 921

Text #9

Max Range: 5.0118. Min Range: -5.0118

Max Act: 4.6533. Min Act: -0.1700

Data Index: 8560627 (Open Web Text)

Max Activating Token Index: 543

Text #10

Max Range: 5.0118. Min Range: -5.0118

Max Act: 4.6223. Min Act: -0.1700

Data Index: 3552746 (Open Web Text)

Max Activating Token Index: 603

Text #11

Max Range: 5.0118. Min Range: -5.0118

Max Act: 4.6154. Min Act: -0.1700

Data Index: 2892233 (Open Web Text)

Max Activating Token Index: 787

Text #12

Max Range: 5.0118. Min Range: -5.0118

Max Act: 4.6062. Min Act: -0.1700

Data Index: 3017219 (Open Web Text)

Max Activating Token Index: 248

Text #13

Max Range: 5.0118. Min Range: -5.0118

Max Act: 4.6147. Min Act: -0.1700

Data Index: 8413767 (Open Web Text)

Max Activating Token Index: 889

Text #14

Max Range: 5.0118. Min Range: -5.0118

Max Act: 4.6022. Min Act: -0.1700

Data Index: 1202578 (Open Web Text)

Max Activating Token Index: 712

Text #15

Max Range: 5.0118. Min Range: -5.0118

Max Act: 4.5918. Min Act: -0.1700

Data Index: 7790835 (Open Web Text)

Max Activating Token Index: 747

Text #16

Max Range: 5.0118. Min Range: -5.0118

Max Act: 4.5523. Min Act: -0.1700

Data Index: 927503 (Open Web Text)

Max Activating Token Index: 420

Text #17

Max Range: 5.0118. Min Range: -5.0118

Max Act: 4.5831. Min Act: -0.1700

Data Index: 2148971 (Open Web Text)

Max Activating Token Index: 908

Text #18

Max Range: 5.0118. Min Range: -5.0118

Max Act: 4.5736. Min Act: -0.1700

Data Index: 1236342 (Open Web Text)

Max Activating Token Index: 508

Text #19

Max Range: 5.0118. Min Range: -5.0118

Max Act: 4.5924. Min Act: -0.1700

Data Index: 5641845 (Open Web Text)

Max Activating Token Index: 981