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

Dataset: Open Web Text

Neuron 2123 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: 4.1450. Min Range: -4.1450

Max Act: 4.1450. Min Act: -0.1700

Data Index: 3949755 (Open Web Text)

Max Activating Token Index: 794

Text #1

Max Range: 4.1450. Min Range: -4.1450

Max Act: 4.0759. Min Act: -0.1700

Data Index: 3438448 (Open Web Text)

Max Activating Token Index: 262

Text #2

Max Range: 4.1450. Min Range: -4.1450

Max Act: 4.0338. Min Act: -0.1700

Data Index: 635723 (Open Web Text)

Max Activating Token Index: 232

Text #3

Max Range: 4.1450. Min Range: -4.1450

Max Act: 4.0265. Min Act: -0.1700

Data Index: 7645164 (Open Web Text)

Max Activating Token Index: 104

Text #4

Max Range: 4.1450. Min Range: -4.1450

Max Act: 3.9427. Min Act: -0.1700

Data Index: 4586767 (Open Web Text)

Max Activating Token Index: 680

Text #5

Max Range: 4.1450. Min Range: -4.1450

Max Act: 3.8442. Min Act: -0.1700

Data Index: 2064778 (Open Web Text)

Max Activating Token Index: 172

Text #6

Max Range: 4.1450. Min Range: -4.1450

Max Act: 3.8589. Min Act: -0.1700

Data Index: 5777216 (Open Web Text)

Max Activating Token Index: 511

Text #7

Max Range: 4.1450. Min Range: -4.1450

Max Act: 3.8625. Min Act: -0.1700

Data Index: 2296633 (Open Web Text)

Max Activating Token Index: 582

Text #8

Max Range: 4.1450. Min Range: -4.1450

Max Act: 3.8387. Min Act: -0.1700

Data Index: 7157144 (Open Web Text)

Max Activating Token Index: 123

Text #9

Max Range: 4.1450. Min Range: -4.1450

Max Act: 3.8401. Min Act: -0.1700

Data Index: 7891322 (Open Web Text)

Max Activating Token Index: 578

Text #10

Max Range: 4.1450. Min Range: -4.1450

Max Act: 3.7954. Min Act: -0.1700

Data Index: 3832828 (Open Web Text)

Max Activating Token Index: 112

Text #11

Max Range: 4.1450. Min Range: -4.1450

Max Act: 3.7748. Min Act: -0.1700

Data Index: 1085680 (Open Web Text)

Max Activating Token Index: 797

Text #12

Max Range: 4.1450. Min Range: -4.1450

Max Act: 3.7204. Min Act: -0.1700

Data Index: 2803167 (Open Web Text)

Max Activating Token Index: 949

Text #13

Max Range: 4.1450. Min Range: -4.1450

Max Act: 3.7610. Min Act: -0.1700

Data Index: 2154030 (Open Web Text)

Max Activating Token Index: 803

Text #14

Max Range: 4.1450. Min Range: -4.1450

Max Act: 3.7597. Min Act: -0.1700

Data Index: 7947026 (Open Web Text)

Max Activating Token Index: 959

Text #15

Max Range: 4.1450. Min Range: -4.1450

Max Act: 3.7308. Min Act: -0.1700

Data Index: 3812915 (Open Web Text)

Max Activating Token Index: 491

Text #16

Max Range: 4.1450. Min Range: -4.1450

Max Act: 3.6856. Min Act: -0.1700

Data Index: 6949641 (Open Web Text)

Max Activating Token Index: 406

Text #17

Max Range: 4.1450. Min Range: -4.1450

Max Act: 3.7216. Min Act: -0.1700

Data Index: 6488751 (Open Web Text)

Max Activating Token Index: 240

Text #18

Max Range: 4.1450. Min Range: -4.1450

Max Act: 3.7042. Min Act: -0.1700

Data Index: 91719 (Open Web Text)

Max Activating Token Index: 299

Text #19

Max Range: 4.1450. Min Range: -4.1450

Max Act: 3.7031. Min Act: -0.1700

Data Index: 2156275 (Open Web Text)

Max Activating Token Index: 156