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

Dataset: Open Web Text

Neuron 2152 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: 6.1262. Min Range: -6.1262

Max Act: 6.1262. Min Act: -0.1700

Data Index: 4416489 (Open Web Text)

Max Activating Token Index: 788

Text #1

Max Range: 6.1262. Min Range: -6.1262

Max Act: 5.8768. Min Act: -0.1700

Data Index: 1755513 (Open Web Text)

Max Activating Token Index: 860

Text #2

Max Range: 6.1262. Min Range: -6.1262

Max Act: 5.8277. Min Act: -0.1700

Data Index: 3346544 (Open Web Text)

Max Activating Token Index: 618

Text #3

Max Range: 6.1262. Min Range: -6.1262

Max Act: 5.8148. Min Act: -0.1700

Data Index: 5129814 (Open Web Text)

Max Activating Token Index: 758

Text #4

Max Range: 6.1262. Min Range: -6.1262

Max Act: 5.7878. Min Act: -0.1700

Data Index: 2004873 (Open Web Text)

Max Activating Token Index: 876

Text #5

Max Range: 6.1262. Min Range: -6.1262

Max Act: 5.8237. Min Act: -0.1700

Data Index: 7526447 (Open Web Text)

Max Activating Token Index: 167

Text #6

Max Range: 6.1262. Min Range: -6.1262

Max Act: 5.8147. Min Act: -0.1700

Data Index: 3137850 (Open Web Text)

Max Activating Token Index: 917

Text #7

Max Range: 6.1262. Min Range: -6.1262

Max Act: 5.8049. Min Act: -0.1700

Data Index: 8531318 (Open Web Text)

Max Activating Token Index: 930

Text #8

Max Range: 6.1262. Min Range: -6.1262

Max Act: 5.7617. Min Act: -0.1700

Data Index: 8435374 (Open Web Text)

Max Activating Token Index: 687

Text #9

Max Range: 6.1262. Min Range: -6.1262

Max Act: 5.7635. Min Act: -0.1700

Data Index: 3753797 (Open Web Text)

Max Activating Token Index: 741

Text #10

Max Range: 6.1262. Min Range: -6.1262

Max Act: 5.7645. Min Act: -0.1700

Data Index: 1723032 (Open Web Text)

Max Activating Token Index: 913

Text #11

Max Range: 6.1262. Min Range: -6.1262

Max Act: 5.7317. Min Act: -0.1700

Data Index: 2206849 (Open Web Text)

Max Activating Token Index: 989

Text #12

Max Range: 6.1262. Min Range: -6.1262

Max Act: 5.7117. Min Act: -0.1700

Data Index: 2539637 (Open Web Text)

Max Activating Token Index: 658

Text #13

Max Range: 6.1262. Min Range: -6.1262

Max Act: 5.6774. Min Act: -0.1700

Data Index: 8127824 (Open Web Text)

Max Activating Token Index: 928

Text #14

Max Range: 6.1262. Min Range: -6.1262

Max Act: 5.6458. Min Act: -0.1700

Data Index: 6762262 (Open Web Text)

Max Activating Token Index: 184

Text #15

Max Range: 6.1262. Min Range: -6.1262

Max Act: 5.6974. Min Act: -0.1700

Data Index: 8717752 (Open Web Text)

Max Activating Token Index: 904

Text #16

Max Range: 6.1262. Min Range: -6.1262

Max Act: 5.6480. Min Act: -0.1700

Data Index: 6238375 (Open Web Text)

Max Activating Token Index: 897

Text #17

Max Range: 6.1262. Min Range: -6.1262

Max Act: 5.6577. Min Act: -0.1700

Data Index: 4150260 (Open Web Text)

Max Activating Token Index: 369

Text #18

Max Range: 6.1262. Min Range: -6.1262

Max Act: 5.6146. Min Act: -0.1700

Data Index: 5458058 (Open Web Text)

Max Activating Token Index: 485

Text #19

Max Range: 6.1262. Min Range: -6.1262

Max Act: 5.6366. Min Act: -0.1700

Data Index: 4390774 (Open Web Text)

Max Activating Token Index: 474