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

Dataset: Open Web Text

Neuron 1814 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: 4.7203. Min Range: -4.7203

Max Act: 4.7203. Min Act: -0.1700

Data Index: 2409312 (Open Web Text)

Max Activating Token Index: 748

Text #1

Max Range: 4.7203. Min Range: -4.7203

Max Act: 4.7061. Min Act: -0.1700

Data Index: 6003610 (Open Web Text)

Max Activating Token Index: 881

Text #2

Max Range: 4.7203. Min Range: -4.7203

Max Act: 4.6568. Min Act: -0.1700

Data Index: 1341479 (Open Web Text)

Max Activating Token Index: 352

Text #3

Max Range: 4.7203. Min Range: -4.7203

Max Act: 4.6357. Min Act: -0.1700

Data Index: 7091433 (Open Web Text)

Max Activating Token Index: 650

Text #4

Max Range: 4.7203. Min Range: -4.7203

Max Act: 4.6474. Min Act: -0.1700

Data Index: 5868848 (Open Web Text)

Max Activating Token Index: 595

Text #5

Max Range: 4.7203. Min Range: -4.7203

Max Act: 4.6111. Min Act: -0.1700

Data Index: 1185702 (Open Web Text)

Max Activating Token Index: 915

Text #6

Max Range: 4.7203. Min Range: -4.7203

Max Act: 4.6431. Min Act: -0.1700

Data Index: 538445 (Open Web Text)

Max Activating Token Index: 209

Text #7

Max Range: 4.7203. Min Range: -4.7203

Max Act: 4.5944. Min Act: -0.1700

Data Index: 4548841 (Open Web Text)

Max Activating Token Index: 438

Text #8

Max Range: 4.7203. Min Range: -4.7203

Max Act: 4.5684. Min Act: -0.1700

Data Index: 2872227 (Open Web Text)

Max Activating Token Index: 249

Text #9

Max Range: 4.7203. Min Range: -4.7203

Max Act: 4.5713. Min Act: -0.1700

Data Index: 4022259 (Open Web Text)

Max Activating Token Index: 320

Text #10

Max Range: 4.7203. Min Range: -4.7203

Max Act: 4.5614. Min Act: -0.1700

Data Index: 6230854 (Open Web Text)

Max Activating Token Index: 779

Text #11

Max Range: 4.7203. Min Range: -4.7203

Max Act: 4.5715. Min Act: -0.1700

Data Index: 5497634 (Open Web Text)

Max Activating Token Index: 641

Text #12

Max Range: 4.7203. Min Range: -4.7203

Max Act: 4.5465. Min Act: -0.1700

Data Index: 1247562 (Open Web Text)

Max Activating Token Index: 540

Text #13

Max Range: 4.7203. Min Range: -4.7203

Max Act: 4.5370. Min Act: -0.1700

Data Index: 8532386 (Open Web Text)

Max Activating Token Index: 749

Text #14

Max Range: 4.7203. Min Range: -4.7203

Max Act: 4.5385. Min Act: -0.1700

Data Index: 4267255 (Open Web Text)

Max Activating Token Index: 426

Text #15

Max Range: 4.7203. Min Range: -4.7203

Max Act: 4.5259. Min Act: -0.1700

Data Index: 6933801 (Open Web Text)

Max Activating Token Index: 178

Text #16

Max Range: 4.7203. Min Range: -4.7203

Max Act: 4.5613. Min Act: -0.1700

Data Index: 7205149 (Open Web Text)

Max Activating Token Index: 370

Text #17

Max Range: 4.7203. Min Range: -4.7203

Max Act: 4.5589. Min Act: -0.1700

Data Index: 7114291 (Open Web Text)

Max Activating Token Index: 169

Text #18

Max Range: 4.7203. Min Range: -4.7203

Max Act: 4.5632. Min Act: -0.1700

Data Index: 3329784 (Open Web Text)

Max Activating Token Index: 140

Text #19

Max Range: 4.7203. Min Range: -4.7203

Max Act: 4.5072. Min Act: -0.1700

Data Index: 3079638 (Open Web Text)

Max Activating Token Index: 910