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

Dataset: Open Web Text

Neuron 1768 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: 4.0245. Min Range: -4.0245

Max Act: 4.0245. Min Act: -0.1700

Data Index: 716794 (Open Web Text)

Max Activating Token Index: 300

Text #1

Max Range: 4.0245. Min Range: -4.0245

Max Act: 3.9734. Min Act: -0.1700

Data Index: 716798 (Open Web Text)

Max Activating Token Index: 30

Text #2

Max Range: 4.0245. Min Range: -4.0245

Max Act: 3.8951. Min Act: -0.1700

Data Index: 6792978 (Open Web Text)

Max Activating Token Index: 389

Text #3

Max Range: 4.0245. Min Range: -4.0245

Max Act: 3.8092. Min Act: -0.1700

Data Index: 3368087 (Open Web Text)

Max Activating Token Index: 393

Text #4

Max Range: 4.0245. Min Range: -4.0245

Max Act: 3.8025. Min Act: -0.1700

Data Index: 3845544 (Open Web Text)

Max Activating Token Index: 406

Text #5

Max Range: 4.0245. Min Range: -4.0245

Max Act: 3.7956. Min Act: -0.1700

Data Index: 1353833 (Open Web Text)

Max Activating Token Index: 39

Text #6

Max Range: 4.0245. Min Range: -4.0245

Max Act: 3.7936. Min Act: -0.1700

Data Index: 2848777 (Open Web Text)

Max Activating Token Index: 427

Text #7

Max Range: 4.0245. Min Range: -4.0245

Max Act: 3.7842. Min Act: -0.1700

Data Index: 3574796 (Open Web Text)

Max Activating Token Index: 414

Text #8

Max Range: 4.0245. Min Range: -4.0245

Max Act: 3.7791. Min Act: -0.1700

Data Index: 1953946 (Open Web Text)

Max Activating Token Index: 18

Text #9

Max Range: 4.0245. Min Range: -4.0245

Max Act: 3.7707. Min Act: -0.1700

Data Index: 7477033 (Open Web Text)

Max Activating Token Index: 471

Text #10

Max Range: 4.0245. Min Range: -4.0245

Max Act: 3.7705. Min Act: -0.1700

Data Index: 1925793 (Open Web Text)

Max Activating Token Index: 346

Text #11

Max Range: 4.0245. Min Range: -4.0245

Max Act: 3.7923. Min Act: -0.1700

Data Index: 2332685 (Open Web Text)

Max Activating Token Index: 660

Text #12

Max Range: 4.0245. Min Range: -4.0245

Max Act: 3.7256. Min Act: -0.1700

Data Index: 3495323 (Open Web Text)

Max Activating Token Index: 341

Text #13

Max Range: 4.0245. Min Range: -4.0245

Max Act: 3.7488. Min Act: -0.1700

Data Index: 8375210 (Open Web Text)

Max Activating Token Index: 818

Text #14

Max Range: 4.0245. Min Range: -4.0245

Max Act: 3.7479. Min Act: -0.1700

Data Index: 7977353 (Open Web Text)

Max Activating Token Index: 338

Text #15

Max Range: 4.0245. Min Range: -4.0245

Max Act: 3.7393. Min Act: -0.1700

Data Index: 3668009 (Open Web Text)

Max Activating Token Index: 242

Text #16

Max Range: 4.0245. Min Range: -4.0245

Max Act: 3.7463. Min Act: -0.1700

Data Index: 2257928 (Open Web Text)

Max Activating Token Index: 147

Text #17

Max Range: 4.0245. Min Range: -4.0245

Max Act: 3.7374. Min Act: -0.1700

Data Index: 4527395 (Open Web Text)

Max Activating Token Index: 100

Text #18

Max Range: 4.0245. Min Range: -4.0245

Max Act: 3.6706. Min Act: -0.1700

Data Index: 5832514 (Open Web Text)

Max Activating Token Index: 508

Text #19

Max Range: 4.0245. Min Range: -4.0245

Max Act: 3.7279. Min Act: -0.1700

Data Index: 7293957 (Open Web Text)

Max Activating Token Index: 781