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

Dataset: Open Web Text

Neuron 515 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: 4.7503. Min Range: -4.7503

Max Act: 4.7503. Min Act: -0.1700

Data Index: 7705610 (Open Web Text)

Max Activating Token Index: 118

Text #1

Max Range: 4.7503. Min Range: -4.7503

Max Act: 4.7122. Min Act: -0.1700

Data Index: 4107947 (Open Web Text)

Max Activating Token Index: 214

Text #2

Max Range: 4.7503. Min Range: -4.7503

Max Act: 4.6478. Min Act: -0.1700

Data Index: 8582499 (Open Web Text)

Max Activating Token Index: 151

Text #3

Max Range: 4.7503. Min Range: -4.7503

Max Act: 4.5804. Min Act: -0.1700

Data Index: 7288084 (Open Web Text)

Max Activating Token Index: 617

Text #4

Max Range: 4.7503. Min Range: -4.7503

Max Act: 4.5707. Min Act: -0.1700

Data Index: 3195371 (Open Web Text)

Max Activating Token Index: 770

Text #5

Max Range: 4.7503. Min Range: -4.7503

Max Act: 4.6191. Min Act: -0.1700

Data Index: 5859944 (Open Web Text)

Max Activating Token Index: 952

Text #6

Max Range: 4.7503. Min Range: -4.7503

Max Act: 4.5396. Min Act: -0.1700

Data Index: 3082511 (Open Web Text)

Max Activating Token Index: 85

Text #7

Max Range: 4.7503. Min Range: -4.7503

Max Act: 4.5542. Min Act: -0.1700

Data Index: 7301737 (Open Web Text)

Max Activating Token Index: 557

Text #8

Max Range: 4.7503. Min Range: -4.7503

Max Act: 4.5525. Min Act: -0.1700

Data Index: 5125039 (Open Web Text)

Max Activating Token Index: 652

Text #9

Max Range: 4.7503. Min Range: -4.7503

Max Act: 4.5273. Min Act: -0.1700

Data Index: 210761 (Open Web Text)

Max Activating Token Index: 358

Text #10

Max Range: 4.7503. Min Range: -4.7503

Max Act: 4.4600. Min Act: -0.1700

Data Index: 1565351 (Open Web Text)

Max Activating Token Index: 523

Text #11

Max Range: 4.7503. Min Range: -4.7503

Max Act: 4.5044. Min Act: -0.1700

Data Index: 4847591 (Open Web Text)

Max Activating Token Index: 34

Text #12

Max Range: 4.7503. Min Range: -4.7503

Max Act: 4.4837. Min Act: -0.1700

Data Index: 2682184 (Open Web Text)

Max Activating Token Index: 254

Text #13

Max Range: 4.7503. Min Range: -4.7503

Max Act: 4.4702. Min Act: -0.1700

Data Index: 6755703 (Open Web Text)

Max Activating Token Index: 769

Text #14

Max Range: 4.7503. Min Range: -4.7503

Max Act: 4.4908. Min Act: -0.1700

Data Index: 7384538 (Open Web Text)

Max Activating Token Index: 413

Text #15

Max Range: 4.7503. Min Range: -4.7503

Max Act: 4.4801. Min Act: -0.1700

Data Index: 3656921 (Open Web Text)

Max Activating Token Index: 425

Text #16

Max Range: 4.7503. Min Range: -4.7503

Max Act: 4.4567. Min Act: -0.1700

Data Index: 7695916 (Open Web Text)

Max Activating Token Index: 731

Text #17

Max Range: 4.7503. Min Range: -4.7503

Max Act: 4.4600. Min Act: -0.1700

Data Index: 5739236 (Open Web Text)

Max Activating Token Index: 518

Text #18

Max Range: 4.7503. Min Range: -4.7503

Max Act: 4.4685. Min Act: -0.1700

Data Index: 2873670 (Open Web Text)

Max Activating Token Index: 808

Text #19

Max Range: 4.7503. Min Range: -4.7503

Max Act: 4.4699. Min Act: -0.1700

Data Index: 5193649 (Open Web Text)

Max Activating Token Index: 235