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

Dataset: Open Web Text

Neuron 1600 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: 6.4928. Min Range: -6.4928

Max Act: 6.4928. Min Act: -0.1700

Data Index: 3219298 (Open Web Text)

Max Activating Token Index: 129

Text #1

Max Range: 6.4928. Min Range: -6.4928

Max Act: 6.4052. Min Act: -0.1700

Data Index: 6406292 (Open Web Text)

Max Activating Token Index: 519

Text #2

Max Range: 6.4928. Min Range: -6.4928

Max Act: 6.4157. Min Act: -0.1700

Data Index: 7058718 (Open Web Text)

Max Activating Token Index: 358

Text #3

Max Range: 6.4928. Min Range: -6.4928

Max Act: 6.4743. Min Act: -0.1700

Data Index: 4937153 (Open Web Text)

Max Activating Token Index: 492

Text #4

Max Range: 6.4928. Min Range: -6.4928

Max Act: 6.3689. Min Act: -0.1700

Data Index: 3592647 (Open Web Text)

Max Activating Token Index: 715

Text #5

Max Range: 6.4928. Min Range: -6.4928

Max Act: 6.3759. Min Act: -0.1700

Data Index: 5634109 (Open Web Text)

Max Activating Token Index: 155

Text #6

Max Range: 6.4928. Min Range: -6.4928

Max Act: 6.3515. Min Act: -0.1700

Data Index: 2180941 (Open Web Text)

Max Activating Token Index: 371

Text #7

Max Range: 6.4928. Min Range: -6.4928

Max Act: 6.3080. Min Act: -0.1700

Data Index: 8369045 (Open Web Text)

Max Activating Token Index: 608

Text #8

Max Range: 6.4928. Min Range: -6.4928

Max Act: 6.3127. Min Act: -0.1700

Data Index: 8825007 (Open Web Text)

Max Activating Token Index: 500

Text #9

Max Range: 6.4928. Min Range: -6.4928

Max Act: 6.2900. Min Act: -0.1700

Data Index: 2386799 (Open Web Text)

Max Activating Token Index: 451

Text #10

Max Range: 6.4928. Min Range: -6.4928

Max Act: 6.2931. Min Act: -0.1700

Data Index: 6735127 (Open Web Text)

Max Activating Token Index: 292

Text #11

Max Range: 6.4928. Min Range: -6.4928

Max Act: 6.3665. Min Act: -0.1700

Data Index: 7836911 (Open Web Text)

Max Activating Token Index: 484

Text #12

Max Range: 6.4928. Min Range: -6.4928

Max Act: 6.3417. Min Act: -0.1700

Data Index: 8804984 (Open Web Text)

Max Activating Token Index: 906

Text #13

Max Range: 6.4928. Min Range: -6.4928

Max Act: 6.3085. Min Act: -0.1700

Data Index: 4246070 (Open Web Text)

Max Activating Token Index: 652

Text #14

Max Range: 6.4928. Min Range: -6.4928

Max Act: 6.2941. Min Act: -0.1700

Data Index: 2545395 (Open Web Text)

Max Activating Token Index: 159

Text #15

Max Range: 6.4928. Min Range: -6.4928

Max Act: 6.2743. Min Act: -0.1700

Data Index: 4198167 (Open Web Text)

Max Activating Token Index: 82

Text #16

Max Range: 6.4928. Min Range: -6.4928

Max Act: 6.2837. Min Act: -0.1700

Data Index: 7191003 (Open Web Text)

Max Activating Token Index: 622

Text #17

Max Range: 6.4928. Min Range: -6.4928

Max Act: 6.2771. Min Act: -0.1700

Data Index: 877092 (Open Web Text)

Max Activating Token Index: 912

Text #18

Max Range: 6.4928. Min Range: -6.4928

Max Act: 6.2682. Min Act: -0.1700

Data Index: 7458971 (Open Web Text)

Max Activating Token Index: 908

Text #19

Max Range: 6.4928. Min Range: -6.4928

Max Act: 6.2476. Min Act: -0.1700

Data Index: 5196263 (Open Web Text)

Max Activating Token Index: 47