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

Dataset: Open Web Text

Neuron 2076 in Layer 1

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: 1.9897. Min Range: -1.9897

Max Act: 1.9897. Min Act: -0.1700

Data Index: 7109072 (Open Web Text)

Max Activating Token Index: 658

Text #1

Max Range: 1.9897. Min Range: -1.9897

Max Act: 1.9643. Min Act: -0.1700

Data Index: 8496529 (Open Web Text)

Max Activating Token Index: 514

Text #2

Max Range: 1.9897. Min Range: -1.9897

Max Act: 1.9500. Min Act: -0.1700

Data Index: 1522943 (Open Web Text)

Max Activating Token Index: 680

Text #3

Max Range: 1.9897. Min Range: -1.9897

Max Act: 1.9356. Min Act: -0.1700

Data Index: 3354460 (Open Web Text)

Max Activating Token Index: 141

Text #4

Max Range: 1.9897. Min Range: -1.9897

Max Act: 1.9371. Min Act: -0.1700

Data Index: 8201750 (Open Web Text)

Max Activating Token Index: 483

Text #5

Max Range: 1.9897. Min Range: -1.9897

Max Act: 1.9278. Min Act: -0.1700

Data Index: 5760327 (Open Web Text)

Max Activating Token Index: 684

Text #6

Max Range: 1.9897. Min Range: -1.9897

Max Act: 1.9367. Min Act: -0.1700

Data Index: 2395419 (Open Web Text)

Max Activating Token Index: 913

Text #7

Max Range: 1.9897. Min Range: -1.9897

Max Act: 1.9226. Min Act: -0.1700

Data Index: 6578879 (Open Web Text)

Max Activating Token Index: 155

Text #8

Max Range: 1.9897. Min Range: -1.9897

Max Act: 1.9145. Min Act: -0.1700

Data Index: 3374988 (Open Web Text)

Max Activating Token Index: 112

Text #9

Max Range: 1.9897. Min Range: -1.9897

Max Act: 1.9161. Min Act: -0.1699

Data Index: 7381076 (Open Web Text)

Max Activating Token Index: 36

Text #10

Max Range: 1.9897. Min Range: -1.9897

Max Act: 1.9164. Min Act: -0.1698

Data Index: 297190 (Open Web Text)

Max Activating Token Index: 837

Text #11

Max Range: 1.9897. Min Range: -1.9897

Max Act: 1.9222. Min Act: -0.1700

Data Index: 1148831 (Open Web Text)

Max Activating Token Index: 190

Text #12

Max Range: 1.9897. Min Range: -1.9897

Max Act: 1.9081. Min Act: -0.1700

Data Index: 3259439 (Open Web Text)

Max Activating Token Index: 540

Text #13

Max Range: 1.9897. Min Range: -1.9897

Max Act: 1.9028. Min Act: -0.1631

Data Index: 423985 (Open Web Text)

Max Activating Token Index: 759

Text #14

Max Range: 1.9897. Min Range: -1.9897

Max Act: 1.9124. Min Act: -0.1700

Data Index: 5976710 (Open Web Text)

Max Activating Token Index: 397

Text #15

Max Range: 1.9897. Min Range: -1.9897

Max Act: 1.9105. Min Act: -0.1693

Data Index: 902486 (Open Web Text)

Max Activating Token Index: 50

Text #16

Max Range: 1.9897. Min Range: -1.9897

Max Act: 1.9053. Min Act: -0.1694

Data Index: 8250651 (Open Web Text)

Max Activating Token Index: 376

Text #17

Max Range: 1.9897. Min Range: -1.9897

Max Act: 1.9214. Min Act: -0.1700

Data Index: 4562499 (Open Web Text)

Max Activating Token Index: 499

Text #18

Max Range: 1.9897. Min Range: -1.9897

Max Act: 1.9051. Min Act: -0.1700

Data Index: 184747 (Open Web Text)

Max Activating Token Index: 75

Text #19

Max Range: 1.9897. Min Range: -1.9897

Max Act: 1.8837. Min Act: -0.1700

Data Index: 8158168 (Open Web Text)

Max Activating Token Index: 100