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

Dataset: Open Web Text

Neuron 655 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: 4.2671. Min Range: -4.2671

Max Act: 4.2671. Min Act: -0.1700

Data Index: 2164754 (Open Web Text)

Max Activating Token Index: 827

Text #1

Max Range: 4.2671. Min Range: -4.2671

Max Act: 4.0913. Min Act: -0.1700

Data Index: 2241868 (Open Web Text)

Max Activating Token Index: 581

Text #2

Max Range: 4.2671. Min Range: -4.2671

Max Act: 4.0835. Min Act: -0.1700

Data Index: 5726682 (Open Web Text)

Max Activating Token Index: 902

Text #3

Max Range: 4.2671. Min Range: -4.2671

Max Act: 4.0932. Min Act: -0.1700

Data Index: 2663007 (Open Web Text)

Max Activating Token Index: 926

Text #4

Max Range: 4.2671. Min Range: -4.2671

Max Act: 4.0591. Min Act: -0.1700

Data Index: 3228496 (Open Web Text)

Max Activating Token Index: 422

Text #5

Max Range: 4.2671. Min Range: -4.2671

Max Act: 4.0532. Min Act: -0.1700

Data Index: 2387024 (Open Web Text)

Max Activating Token Index: 314

Text #6

Max Range: 4.2671. Min Range: -4.2671

Max Act: 4.0663. Min Act: -0.1700

Data Index: 8697424 (Open Web Text)

Max Activating Token Index: 192

Text #7

Max Range: 4.2671. Min Range: -4.2671

Max Act: 4.0766. Min Act: -0.1700

Data Index: 6248988 (Open Web Text)

Max Activating Token Index: 951

Text #8

Max Range: 4.2671. Min Range: -4.2671

Max Act: 4.0700. Min Act: -0.1700

Data Index: 2412879 (Open Web Text)

Max Activating Token Index: 224

Text #9

Max Range: 4.2671. Min Range: -4.2671

Max Act: 4.0961. Min Act: -0.1700

Data Index: 5408903 (Open Web Text)

Max Activating Token Index: 678

Text #10

Max Range: 4.2671. Min Range: -4.2671

Max Act: 4.0771. Min Act: -0.1700

Data Index: 4845185 (Open Web Text)

Max Activating Token Index: 317

Text #11

Max Range: 4.2671. Min Range: -4.2671

Max Act: 4.0296. Min Act: -0.1700

Data Index: 6600155 (Open Web Text)

Max Activating Token Index: 194

Text #12

Max Range: 4.2671. Min Range: -4.2671

Max Act: 4.0513. Min Act: -0.1700

Data Index: 4078 (Open Web Text)

Max Activating Token Index: 956

Text #13

Max Range: 4.2671. Min Range: -4.2671

Max Act: 4.0582. Min Act: -0.1700

Data Index: 1195595 (Open Web Text)

Max Activating Token Index: 490

Text #14

Max Range: 4.2671. Min Range: -4.2671

Max Act: 4.0275. Min Act: -0.1700

Data Index: 7208222 (Open Web Text)

Max Activating Token Index: 510

Text #15

Max Range: 4.2671. Min Range: -4.2671

Max Act: 4.0399. Min Act: -0.1700

Data Index: 7595952 (Open Web Text)

Max Activating Token Index: 542

Text #16

Max Range: 4.2671. Min Range: -4.2671

Max Act: 4.0345. Min Act: -0.1700

Data Index: 2018269 (Open Web Text)

Max Activating Token Index: 213

Text #17

Max Range: 4.2671. Min Range: -4.2671

Max Act: 4.0541. Min Act: -0.1700

Data Index: 7740109 (Open Web Text)

Max Activating Token Index: 221

Text #18

Max Range: 4.2671. Min Range: -4.2671

Max Act: 4.0218. Min Act: -0.1700

Data Index: 5301070 (Open Web Text)

Max Activating Token Index: 845

Text #19

Max Range: 4.2671. Min Range: -4.2671

Max Act: 4.0038. Min Act: -0.1700

Data Index: 3566132 (Open Web Text)

Max Activating Token Index: 873