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

Dataset: Open Web Text

Neuron 1465 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: 4.1986. Min Range: -4.1986

Max Act: 4.1861. Min Act: -0.1700

Data Index: 4706185 (Open Web Text)

Max Activating Token Index: 906

Text #1

Max Range: 4.1986. Min Range: -4.1986

Max Act: 4.1819. Min Act: -0.1700

Data Index: 2721439 (Open Web Text)

Max Activating Token Index: 300

Text #2

Max Range: 4.1986. Min Range: -4.1986

Max Act: 4.1986. Min Act: -0.1700

Data Index: 5266762 (Open Web Text)

Max Activating Token Index: 582

Text #3

Max Range: 4.1986. Min Range: -4.1986

Max Act: 4.1618. Min Act: -0.1700

Data Index: 621532 (Open Web Text)

Max Activating Token Index: 490

Text #4

Max Range: 4.1986. Min Range: -4.1986

Max Act: 4.1270. Min Act: -0.1700

Data Index: 1386073 (Open Web Text)

Max Activating Token Index: 463

Text #5

Max Range: 4.1986. Min Range: -4.1986

Max Act: 4.1364. Min Act: -0.1700

Data Index: 5789391 (Open Web Text)

Max Activating Token Index: 233

Text #6

Max Range: 4.1986. Min Range: -4.1986

Max Act: 4.1628. Min Act: -0.1700

Data Index: 676965 (Open Web Text)

Max Activating Token Index: 295

Text #7

Max Range: 4.1986. Min Range: -4.1986

Max Act: 4.1352. Min Act: -0.1700

Data Index: 7531577 (Open Web Text)

Max Activating Token Index: 590

Text #8

Max Range: 4.1986. Min Range: -4.1986

Max Act: 4.1385. Min Act: -0.1700

Data Index: 587248 (Open Web Text)

Max Activating Token Index: 207

Text #9

Max Range: 4.1986. Min Range: -4.1986

Max Act: 4.1055. Min Act: -0.1700

Data Index: 6142536 (Open Web Text)

Max Activating Token Index: 296

Text #10

Max Range: 4.1986. Min Range: -4.1986

Max Act: 4.0979. Min Act: -0.1700

Data Index: 6041911 (Open Web Text)

Max Activating Token Index: 446

Text #11

Max Range: 4.1986. Min Range: -4.1986

Max Act: 4.1218. Min Act: -0.1700

Data Index: 1974788 (Open Web Text)

Max Activating Token Index: 981

Text #12

Max Range: 4.1986. Min Range: -4.1986

Max Act: 4.0937. Min Act: -0.1700

Data Index: 1762655 (Open Web Text)

Max Activating Token Index: 453

Text #13

Max Range: 4.1986. Min Range: -4.1986

Max Act: 4.0862. Min Act: -0.1700

Data Index: 3092743 (Open Web Text)

Max Activating Token Index: 911

Text #14

Max Range: 4.1986. Min Range: -4.1986

Max Act: 4.1062. Min Act: -0.1700

Data Index: 4595461 (Open Web Text)

Max Activating Token Index: 729

Text #15

Max Range: 4.1986. Min Range: -4.1986

Max Act: 4.1208. Min Act: -0.1700

Data Index: 7281241 (Open Web Text)

Max Activating Token Index: 347

Text #16

Max Range: 4.1986. Min Range: -4.1986

Max Act: 4.1170. Min Act: -0.1700

Data Index: 3710042 (Open Web Text)

Max Activating Token Index: 450

Text #17

Max Range: 4.1986. Min Range: -4.1986

Max Act: 4.1151. Min Act: -0.1700

Data Index: 6283424 (Open Web Text)

Max Activating Token Index: 519

Text #18

Max Range: 4.1986. Min Range: -4.1986

Max Act: 4.0705. Min Act: -0.1700

Data Index: 5664576 (Open Web Text)

Max Activating Token Index: 228

Text #19

Max Range: 4.1986. Min Range: -4.1986

Max Act: 4.0947. Min Act: -0.1700

Data Index: 4806458 (Open Web Text)

Max Activating Token Index: 243