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

Dataset: Open Web Text

Neuron 2416 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: 3.5559. Min Range: -3.5559

Max Act: 3.5559. Min Act: -0.1700

Data Index: 6638676 (Open Web Text)

Max Activating Token Index: 995

Text #1

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.5242. Min Act: -0.1700

Data Index: 5741167 (Open Web Text)

Max Activating Token Index: 925

Text #2

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.5208. Min Act: -0.1700

Data Index: 5581109 (Open Web Text)

Max Activating Token Index: 138

Text #3

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.5159. Min Act: -0.1700

Data Index: 8001678 (Open Web Text)

Max Activating Token Index: 128

Text #4

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.4802. Min Act: -0.1700

Data Index: 602207 (Open Web Text)

Max Activating Token Index: 692

Text #5

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.4837. Min Act: -0.1700

Data Index: 129949 (Open Web Text)

Max Activating Token Index: 417

Text #6

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.4402. Min Act: -0.1700

Data Index: 7391761 (Open Web Text)

Max Activating Token Index: 426

Text #7

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.4593. Min Act: -0.1700

Data Index: 2082516 (Open Web Text)

Max Activating Token Index: 15

Text #8

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.4557. Min Act: -0.1700

Data Index: 7153572 (Open Web Text)

Max Activating Token Index: 589

Text #9

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.4467. Min Act: -0.1700

Data Index: 7974433 (Open Web Text)

Max Activating Token Index: 104

Text #10

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.4412. Min Act: -0.1700

Data Index: 2388595 (Open Web Text)

Max Activating Token Index: 465

Text #11

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.4464. Min Act: -0.1700

Data Index: 4778368 (Open Web Text)

Max Activating Token Index: 407

Text #12

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.4684. Min Act: -0.1700

Data Index: 5052294 (Open Web Text)

Max Activating Token Index: 501

Text #13

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.4655. Min Act: -0.1700

Data Index: 2818889 (Open Web Text)

Max Activating Token Index: 333

Text #14

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.4608. Min Act: -0.1700

Data Index: 8285424 (Open Web Text)

Max Activating Token Index: 532

Text #15

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.4482. Min Act: -0.1700

Data Index: 2087845 (Open Web Text)

Max Activating Token Index: 555

Text #16

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.4462. Min Act: -0.1700

Data Index: 7133748 (Open Web Text)

Max Activating Token Index: 477

Text #17

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.4210. Min Act: -0.1700

Data Index: 3241496 (Open Web Text)

Max Activating Token Index: 952

Text #18

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.4128. Min Act: -0.1700

Data Index: 1279829 (Open Web Text)

Max Activating Token Index: 695

Text #19

Max Range: 3.5559. Min Range: -3.5559

Max Act: 3.4415. Min Act: -0.1700

Data Index: 7742535 (Open Web Text)

Max Activating Token Index: 48