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

Dataset: Open Web Text

Neuron 1281 in Layer 3

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: 4.3321. Min Range: -4.3321

Max Act: 4.3321. Min Act: -0.1700

Data Index: 6238377 (Open Web Text)

Max Activating Token Index: 912

Text #1

Max Range: 4.3321. Min Range: -4.3321

Max Act: 4.2960. Min Act: -0.1700

Data Index: 5998739 (Open Web Text)

Max Activating Token Index: 153

Text #2

Max Range: 4.3321. Min Range: -4.3321

Max Act: 4.2617. Min Act: -0.1700

Data Index: 7805845 (Open Web Text)

Max Activating Token Index: 845

Text #3

Max Range: 4.3321. Min Range: -4.3321

Max Act: 4.2626. Min Act: -0.1700

Data Index: 841844 (Open Web Text)

Max Activating Token Index: 359

Text #4

Max Range: 4.3321. Min Range: -4.3321

Max Act: 4.2171. Min Act: -0.1700

Data Index: 8214474 (Open Web Text)

Max Activating Token Index: 865

Text #5

Max Range: 4.3321. Min Range: -4.3321

Max Act: 4.2352. Min Act: -0.1700

Data Index: 4393071 (Open Web Text)

Max Activating Token Index: 48

Text #6

Max Range: 4.3321. Min Range: -4.3321

Max Act: 4.2287. Min Act: -0.1700

Data Index: 2696826 (Open Web Text)

Max Activating Token Index: 68

Text #7

Max Range: 4.3321. Min Range: -4.3321

Max Act: 4.2412. Min Act: -0.1700

Data Index: 4050843 (Open Web Text)

Max Activating Token Index: 117

Text #8

Max Range: 4.3321. Min Range: -4.3321

Max Act: 4.2531. Min Act: -0.1700

Data Index: 1783349 (Open Web Text)

Max Activating Token Index: 497

Text #9

Max Range: 4.3321. Min Range: -4.3321

Max Act: 4.1988. Min Act: -0.1700

Data Index: 7119004 (Open Web Text)

Max Activating Token Index: 344

Text #10

Max Range: 4.3321. Min Range: -4.3321

Max Act: 4.2067. Min Act: -0.1700

Data Index: 8779564 (Open Web Text)

Max Activating Token Index: 147

Text #11

Max Range: 4.3321. Min Range: -4.3321

Max Act: 4.2092. Min Act: -0.1700

Data Index: 8643293 (Open Web Text)

Max Activating Token Index: 180

Text #12

Max Range: 4.3321. Min Range: -4.3321

Max Act: 4.2197. Min Act: -0.1700

Data Index: 5002372 (Open Web Text)

Max Activating Token Index: 162

Text #13

Max Range: 4.3321. Min Range: -4.3321

Max Act: 4.1915. Min Act: -0.1700

Data Index: 1386422 (Open Web Text)

Max Activating Token Index: 945

Text #14

Max Range: 4.3321. Min Range: -4.3321

Max Act: 4.1888. Min Act: -0.1700

Data Index: 3908892 (Open Web Text)

Max Activating Token Index: 931

Text #15

Max Range: 4.3321. Min Range: -4.3321

Max Act: 4.1821. Min Act: -0.1700

Data Index: 4362966 (Open Web Text)

Max Activating Token Index: 681

Text #16

Max Range: 4.3321. Min Range: -4.3321

Max Act: 4.1994. Min Act: -0.1700

Data Index: 3294493 (Open Web Text)

Max Activating Token Index: 978

Text #17

Max Range: 4.3321. Min Range: -4.3321

Max Act: 4.2230. Min Act: -0.1700

Data Index: 2120683 (Open Web Text)

Max Activating Token Index: 371

Text #18

Max Range: 4.3321. Min Range: -4.3321

Max Act: 4.1840. Min Act: -0.1700

Data Index: 5795641 (Open Web Text)

Max Activating Token Index: 484

Text #19

Max Range: 4.3321. Min Range: -4.3321

Max Act: 4.1674. Min Act: -0.1700

Data Index: 361880 (Open Web Text)

Max Activating Token Index: 133