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

Dataset: Open Web Text

Neuron 1905 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: 3.5973. Min Range: -3.5973

Max Act: 3.5973. Min Act: -0.1700

Data Index: 627172 (Open Web Text)

Max Activating Token Index: 338

Text #1

Max Range: 3.5973. Min Range: -3.5973

Max Act: 3.5436. Min Act: -0.1700

Data Index: 6573369 (Open Web Text)

Max Activating Token Index: 72

Text #2

Max Range: 3.5973. Min Range: -3.5973

Max Act: 3.5083. Min Act: -0.1700

Data Index: 5772753 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.5973. Min Range: -3.5973

Max Act: 3.5204. Min Act: -0.1700

Data Index: 3083532 (Open Web Text)

Max Activating Token Index: 84

Text #4

Max Range: 3.5973. Min Range: -3.5973

Max Act: 3.4998. Min Act: -0.1700

Data Index: 1376699 (Open Web Text)

Max Activating Token Index: 385

Text #5

Max Range: 3.5973. Min Range: -3.5973

Max Act: 3.4739. Min Act: -0.1700

Data Index: 4673895 (Open Web Text)

Max Activating Token Index: 757

Text #6

Max Range: 3.5973. Min Range: -3.5973

Max Act: 3.4851. Min Act: -0.1700

Data Index: 2463480 (Open Web Text)

Max Activating Token Index: 738

Text #7

Max Range: 3.5973. Min Range: -3.5973

Max Act: 3.4847. Min Act: -0.1700

Data Index: 4966236 (Open Web Text)

Max Activating Token Index: 790

Text #8

Max Range: 3.5973. Min Range: -3.5973

Max Act: 3.4393. Min Act: -0.1700

Data Index: 1805599 (Open Web Text)

Max Activating Token Index: 346

Text #9

Max Range: 3.5973. Min Range: -3.5973

Max Act: 3.4519. Min Act: -0.1700

Data Index: 4651698 (Open Web Text)

Max Activating Token Index: 448

Text #10

Max Range: 3.5973. Min Range: -3.5973

Max Act: 3.4449. Min Act: -0.1700

Data Index: 2735357 (Open Web Text)

Max Activating Token Index: 476

Text #11

Max Range: 3.5973. Min Range: -3.5973

Max Act: 3.4402. Min Act: -0.1700

Data Index: 8808104 (Open Web Text)

Max Activating Token Index: 207

Text #12

Max Range: 3.5973. Min Range: -3.5973

Max Act: 3.4507. Min Act: -0.1700

Data Index: 4385494 (Open Web Text)

Max Activating Token Index: 50

Text #13

Max Range: 3.5973. Min Range: -3.5973

Max Act: 3.4397. Min Act: -0.1700

Data Index: 7004495 (Open Web Text)

Max Activating Token Index: 751

Text #14

Max Range: 3.5973. Min Range: -3.5973

Max Act: 3.4607. Min Act: -0.1699

Data Index: 2579267 (Open Web Text)

Max Activating Token Index: 957

Text #15

Max Range: 3.5973. Min Range: -3.5973

Max Act: 3.3986. Min Act: -0.1700

Data Index: 2135009 (Open Web Text)

Max Activating Token Index: 497

Text #16

Max Range: 3.5973. Min Range: -3.5973

Max Act: 3.3854. Min Act: -0.1700

Data Index: 253321 (Open Web Text)

Max Activating Token Index: 397

Text #17

Max Range: 3.5973. Min Range: -3.5973

Max Act: 3.4237. Min Act: -0.1700

Data Index: 117966 (Open Web Text)

Max Activating Token Index: 238

Text #18

Max Range: 3.5973. Min Range: -3.5973

Max Act: 3.3823. Min Act: -0.1700

Data Index: 2656434 (Open Web Text)

Max Activating Token Index: 631

Text #19

Max Range: 3.5973. Min Range: -3.5973

Max Act: 3.3927. Min Act: -0.1700

Data Index: 4451386 (Open Web Text)

Max Activating Token Index: 906