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

Dataset: Open Web Text

Neuron 2890 in Layer 6

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: 4.8488. Min Range: -4.8488

Max Act: 4.8411. Min Act: -0.1700

Data Index: 6101836 (Open Web Text)

Max Activating Token Index: 229

Text #1

Max Range: 4.8488. Min Range: -4.8488

Max Act: 4.8488. Min Act: -0.1700

Data Index: 1596751 (Open Web Text)

Max Activating Token Index: 288

Text #2

Max Range: 4.8488. Min Range: -4.8488

Max Act: 4.7450. Min Act: -0.1700

Data Index: 2746338 (Open Web Text)

Max Activating Token Index: 565

Text #3

Max Range: 4.8488. Min Range: -4.8488

Max Act: 4.7751. Min Act: -0.1700

Data Index: 589186 (Open Web Text)

Max Activating Token Index: 316

Text #4

Max Range: 4.8488. Min Range: -4.8488

Max Act: 4.7928. Min Act: -0.1700

Data Index: 3482531 (Open Web Text)

Max Activating Token Index: 924

Text #5

Max Range: 4.8488. Min Range: -4.8488

Max Act: 4.8034. Min Act: -0.1700

Data Index: 1600337 (Open Web Text)

Max Activating Token Index: 676

Text #6

Max Range: 4.8488. Min Range: -4.8488

Max Act: 4.7485. Min Act: -0.1700

Data Index: 657608 (Open Web Text)

Max Activating Token Index: 354

Text #7

Max Range: 4.8488. Min Range: -4.8488

Max Act: 4.7376. Min Act: -0.1700

Data Index: 8065319 (Open Web Text)

Max Activating Token Index: 325

Text #8

Max Range: 4.8488. Min Range: -4.8488

Max Act: 4.7192. Min Act: -0.1700

Data Index: 3815110 (Open Web Text)

Max Activating Token Index: 505

Text #9

Max Range: 4.8488. Min Range: -4.8488

Max Act: 4.6806. Min Act: -0.1700

Data Index: 477052 (Open Web Text)

Max Activating Token Index: 285

Text #10

Max Range: 4.8488. Min Range: -4.8488

Max Act: 4.6925. Min Act: -0.1700

Data Index: 5282726 (Open Web Text)

Max Activating Token Index: 161

Text #11

Max Range: 4.8488. Min Range: -4.8488

Max Act: 4.7252. Min Act: -0.1700

Data Index: 3380368 (Open Web Text)

Max Activating Token Index: 1006

Text #12

Max Range: 4.8488. Min Range: -4.8488

Max Act: 4.6621. Min Act: -0.1700

Data Index: 2671072 (Open Web Text)

Max Activating Token Index: 427

Text #13

Max Range: 4.8488. Min Range: -4.8488

Max Act: 4.7117. Min Act: -0.1700

Data Index: 4708627 (Open Web Text)

Max Activating Token Index: 608

Text #14

Max Range: 4.8488. Min Range: -4.8488

Max Act: 4.6991. Min Act: -0.1700

Data Index: 1457280 (Open Web Text)

Max Activating Token Index: 310

Text #15

Max Range: 4.8488. Min Range: -4.8488

Max Act: 4.6638. Min Act: -0.1700

Data Index: 3387586 (Open Web Text)

Max Activating Token Index: 741

Text #16

Max Range: 4.8488. Min Range: -4.8488

Max Act: 4.6651. Min Act: -0.1700

Data Index: 6049425 (Open Web Text)

Max Activating Token Index: 413

Text #17

Max Range: 4.8488. Min Range: -4.8488

Max Act: 4.6521. Min Act: -0.1700

Data Index: 2778407 (Open Web Text)

Max Activating Token Index: 81

Text #18

Max Range: 4.8488. Min Range: -4.8488

Max Act: 4.6676. Min Act: -0.1700

Data Index: 245364 (Open Web Text)

Max Activating Token Index: 972

Text #19

Max Range: 4.8488. Min Range: -4.8488

Max Act: 4.7009. Min Act: -0.1700

Data Index: 414524 (Open Web Text)

Max Activating Token Index: 526