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

Dataset: Open Web Text

Neuron 2425 in Layer 4

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: 7.1691. Min Range: -7.1691

Max Act: 7.1691. Min Act: -0.1700

Data Index: 6124265 (Open Web Text)

Max Activating Token Index: 778

Text #1

Max Range: 7.1691. Min Range: -7.1691

Max Act: 7.0261. Min Act: -0.1700

Data Index: 3892524 (Open Web Text)

Max Activating Token Index: 924

Text #2

Max Range: 7.1691. Min Range: -7.1691

Max Act: 6.8299. Min Act: -0.1700

Data Index: 6025376 (Open Web Text)

Max Activating Token Index: 189

Text #3

Max Range: 7.1691. Min Range: -7.1691

Max Act: 6.7364. Min Act: -0.1700

Data Index: 644709 (Open Web Text)

Max Activating Token Index: 484

Text #4

Max Range: 7.1691. Min Range: -7.1691

Max Act: 6.7201. Min Act: -0.1700

Data Index: 67993 (Open Web Text)

Max Activating Token Index: 483

Text #5

Max Range: 7.1691. Min Range: -7.1691

Max Act: 6.6078. Min Act: -0.1700

Data Index: 7497737 (Open Web Text)

Max Activating Token Index: 595

Text #6

Max Range: 7.1691. Min Range: -7.1691

Max Act: 6.6167. Min Act: -0.1700

Data Index: 1398856 (Open Web Text)

Max Activating Token Index: 700

Text #7

Max Range: 7.1691. Min Range: -7.1691

Max Act: 6.5523. Min Act: -0.1700

Data Index: 5521556 (Open Web Text)

Max Activating Token Index: 276

Text #8

Max Range: 7.1691. Min Range: -7.1691

Max Act: 6.4655. Min Act: -0.1700

Data Index: 5040798 (Open Web Text)

Max Activating Token Index: 736

Text #9

Max Range: 7.1691. Min Range: -7.1691

Max Act: 6.5006. Min Act: -0.1700

Data Index: 2985687 (Open Web Text)

Max Activating Token Index: 1016

Text #10

Max Range: 7.1691. Min Range: -7.1691

Max Act: 6.5123. Min Act: -0.1700

Data Index: 6204011 (Open Web Text)

Max Activating Token Index: 543

Text #11

Max Range: 7.1691. Min Range: -7.1691

Max Act: 6.4618. Min Act: -0.1700

Data Index: 5521562 (Open Web Text)

Max Activating Token Index: 474

Text #12

Max Range: 7.1691. Min Range: -7.1691

Max Act: 6.4032. Min Act: -0.1700

Data Index: 3148008 (Open Web Text)

Max Activating Token Index: 569

Text #13

Max Range: 7.1691. Min Range: -7.1691

Max Act: 6.4899. Min Act: -0.1700

Data Index: 8015047 (Open Web Text)

Max Activating Token Index: 763

Text #14

Max Range: 7.1691. Min Range: -7.1691

Max Act: 6.4153. Min Act: -0.1700

Data Index: 7431701 (Open Web Text)

Max Activating Token Index: 834

Text #15

Max Range: 7.1691. Min Range: -7.1691

Max Act: 6.4211. Min Act: -0.1700

Data Index: 7570575 (Open Web Text)

Max Activating Token Index: 542

Text #16

Max Range: 7.1691. Min Range: -7.1691

Max Act: 6.3230. Min Act: -0.1700

Data Index: 2428590 (Open Web Text)

Max Activating Token Index: 430

Text #17

Max Range: 7.1691. Min Range: -7.1691

Max Act: 6.4329. Min Act: -0.1700

Data Index: 4777379 (Open Web Text)

Max Activating Token Index: 83

Text #18

Max Range: 7.1691. Min Range: -7.1691

Max Act: 6.3740. Min Act: -0.1700

Data Index: 4946828 (Open Web Text)

Max Activating Token Index: 697

Text #19

Max Range: 7.1691. Min Range: -7.1691

Max Act: 6.3637. Min Act: -0.1700

Data Index: 6611606 (Open Web Text)

Max Activating Token Index: 167