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

Dataset: Open Web Text

Neuron 2431 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: 1.0130. Min Range: -1.0130

Max Act: 1.0130. Min Act: -0.1450

Data Index: 2821062 (Open Web Text)

Max Activating Token Index: 538

Text #1

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.9861. Min Act: -0.1567

Data Index: 8263772 (Open Web Text)

Max Activating Token Index: 704

Text #2

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.9802. Min Act: -0.1443

Data Index: 7958167 (Open Web Text)

Max Activating Token Index: 719

Text #3

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.9838. Min Act: -0.1700

Data Index: 1952414 (Open Web Text)

Max Activating Token Index: 540

Text #4

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.9714. Min Act: -0.1686

Data Index: 2976250 (Open Web Text)

Max Activating Token Index: 535

Text #5

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.9731. Min Act: -0.1362

Data Index: 5483247 (Open Web Text)

Max Activating Token Index: 545

Text #6

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.9776. Min Act: -0.1697

Data Index: 2318333 (Open Web Text)

Max Activating Token Index: 699

Text #7

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.9806. Min Act: -0.1441

Data Index: 2648312 (Open Web Text)

Max Activating Token Index: 774

Text #8

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.9573. Min Act: -0.1607

Data Index: 2300343 (Open Web Text)

Max Activating Token Index: 545

Text #9

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.9553. Min Act: -0.1283

Data Index: 434448 (Open Web Text)

Max Activating Token Index: 293

Text #10

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.9552. Min Act: -0.1550

Data Index: 5758480 (Open Web Text)

Max Activating Token Index: 592

Text #11

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.9616. Min Act: -0.1467

Data Index: 6116924 (Open Web Text)

Max Activating Token Index: 950

Text #12

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.9579. Min Act: -0.1449

Data Index: 7327910 (Open Web Text)

Max Activating Token Index: 821

Text #13

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.9542. Min Act: -0.1432

Data Index: 3123262 (Open Web Text)

Max Activating Token Index: 659

Text #14

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.9479. Min Act: -0.1630

Data Index: 1527369 (Open Web Text)

Max Activating Token Index: 907

Text #15

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.9512. Min Act: -0.1181

Data Index: 4091219 (Open Web Text)

Max Activating Token Index: 940

Text #16

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.9514. Min Act: -0.1187

Data Index: 7163019 (Open Web Text)

Max Activating Token Index: 760

Text #17

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.9464. Min Act: -0.1378

Data Index: 4063303 (Open Web Text)

Max Activating Token Index: 925

Text #18

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.9457. Min Act: -0.1541

Data Index: 1606324 (Open Web Text)

Max Activating Token Index: 615

Text #19

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.9432. Min Act: -0.1700

Data Index: 1548022 (Open Web Text)

Max Activating Token Index: 257