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

Dataset: Open Web Text

Neuron 2794 in Layer 4

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: 3.1337. Min Range: -3.1337

Max Act: 3.1337. Min Act: -0.1700

Data Index: 5611900 (Open Web Text)

Max Activating Token Index: 394

Text #1

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.9578. Min Act: -0.1700

Data Index: 3527527 (Open Web Text)

Max Activating Token Index: 771

Text #2

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.9226. Min Act: -0.1700

Data Index: 921927 (Open Web Text)

Max Activating Token Index: 1003

Text #3

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.8966. Min Act: -0.1700

Data Index: 1486047 (Open Web Text)

Max Activating Token Index: 66

Text #4

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.9140. Min Act: -0.1700

Data Index: 7321914 (Open Web Text)

Max Activating Token Index: 68

Text #5

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.8751. Min Act: -0.1700

Data Index: 1121907 (Open Web Text)

Max Activating Token Index: 118

Text #6

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.8552. Min Act: -0.1700

Data Index: 4691596 (Open Web Text)

Max Activating Token Index: 150

Text #7

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.8533. Min Act: -0.1700

Data Index: 6257356 (Open Web Text)

Max Activating Token Index: 676

Text #8

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.8442. Min Act: -0.1700

Data Index: 6378959 (Open Web Text)

Max Activating Token Index: 603

Text #9

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.8698. Min Act: -0.1700

Data Index: 8808714 (Open Web Text)

Max Activating Token Index: 310

Text #10

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.8487. Min Act: -0.1700

Data Index: 6257355 (Open Web Text)

Max Activating Token Index: 833

Text #11

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.8473. Min Act: -0.1700

Data Index: 6004820 (Open Web Text)

Max Activating Token Index: 539

Text #12

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.8386. Min Act: -0.1700

Data Index: 3527528 (Open Web Text)

Max Activating Token Index: 628

Text #13

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.8399. Min Act: -0.1700

Data Index: 7072640 (Open Web Text)

Max Activating Token Index: 886

Text #14

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.8308. Min Act: -0.1700

Data Index: 6346623 (Open Web Text)

Max Activating Token Index: 945

Text #15

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.8521. Min Act: -0.1700

Data Index: 6302373 (Open Web Text)

Max Activating Token Index: 583

Text #16

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.8161. Min Act: -0.1700

Data Index: 7389816 (Open Web Text)

Max Activating Token Index: 100

Text #17

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.8369. Min Act: -0.1700

Data Index: 7558001 (Open Web Text)

Max Activating Token Index: 518

Text #18

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.8455. Min Act: -0.1700

Data Index: 1342034 (Open Web Text)

Max Activating Token Index: 447

Text #19

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.8374. Min Act: -0.1700

Data Index: 7968369 (Open Web Text)

Max Activating Token Index: 9