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

Dataset: Open Web Text

Neuron 341 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: 5.4259. Min Range: -5.4259

Max Act: 5.4259. Min Act: -0.1700

Data Index: 2577662 (Open Web Text)

Max Activating Token Index: 115

Text #1

Max Range: 5.4259. Min Range: -5.4259

Max Act: 5.2614. Min Act: -0.1700

Data Index: 4898480 (Open Web Text)

Max Activating Token Index: 644

Text #2

Max Range: 5.4259. Min Range: -5.4259

Max Act: 5.2620. Min Act: -0.1700

Data Index: 166756 (Open Web Text)

Max Activating Token Index: 312

Text #3

Max Range: 5.4259. Min Range: -5.4259

Max Act: 5.2683. Min Act: -0.1700

Data Index: 1346035 (Open Web Text)

Max Activating Token Index: 541

Text #4

Max Range: 5.4259. Min Range: -5.4259

Max Act: 5.1949. Min Act: -0.1700

Data Index: 1124819 (Open Web Text)

Max Activating Token Index: 374

Text #5

Max Range: 5.4259. Min Range: -5.4259

Max Act: 5.2386. Min Act: -0.1700

Data Index: 1753669 (Open Web Text)

Max Activating Token Index: 11

Text #6

Max Range: 5.4259. Min Range: -5.4259

Max Act: 5.2370. Min Act: -0.1700

Data Index: 1363418 (Open Web Text)

Max Activating Token Index: 228

Text #7

Max Range: 5.4259. Min Range: -5.4259

Max Act: 5.2070. Min Act: -0.1700

Data Index: 1093636 (Open Web Text)

Max Activating Token Index: 1002

Text #8

Max Range: 5.4259. Min Range: -5.4259

Max Act: 5.1975. Min Act: -0.1700

Data Index: 3006316 (Open Web Text)

Max Activating Token Index: 359

Text #9

Max Range: 5.4259. Min Range: -5.4259

Max Act: 5.1754. Min Act: -0.1700

Data Index: 453471 (Open Web Text)

Max Activating Token Index: 283

Text #10

Max Range: 5.4259. Min Range: -5.4259

Max Act: 5.1693. Min Act: -0.1700

Data Index: 3037752 (Open Web Text)

Max Activating Token Index: 727

Text #11

Max Range: 5.4259. Min Range: -5.4259

Max Act: 5.0893. Min Act: -0.1700

Data Index: 3335330 (Open Web Text)

Max Activating Token Index: 451

Text #12

Max Range: 5.4259. Min Range: -5.4259

Max Act: 5.1575. Min Act: -0.1700

Data Index: 5531650 (Open Web Text)

Max Activating Token Index: 82

Text #13

Max Range: 5.4259. Min Range: -5.4259

Max Act: 5.1395. Min Act: -0.1700

Data Index: 4350458 (Open Web Text)

Max Activating Token Index: 630

Text #14

Max Range: 5.4259. Min Range: -5.4259

Max Act: 5.0796. Min Act: -0.1700

Data Index: 1657246 (Open Web Text)

Max Activating Token Index: 176

Text #15

Max Range: 5.4259. Min Range: -5.4259

Max Act: 5.0902. Min Act: -0.1700

Data Index: 1753670 (Open Web Text)

Max Activating Token Index: 165

Text #16

Max Range: 5.4259. Min Range: -5.4259

Max Act: 5.0422. Min Act: -0.1700

Data Index: 4397705 (Open Web Text)

Max Activating Token Index: 404

Text #17

Max Range: 5.4259. Min Range: -5.4259

Max Act: 5.0212. Min Act: -0.1700

Data Index: 8588033 (Open Web Text)

Max Activating Token Index: 1004

Text #18

Max Range: 5.4259. Min Range: -5.4259

Max Act: 5.0247. Min Act: -0.1700

Data Index: 1367872 (Open Web Text)

Max Activating Token Index: 649

Text #19

Max Range: 5.4259. Min Range: -5.4259

Max Act: 4.9908. Min Act: -0.1700

Data Index: 501406 (Open Web Text)

Max Activating Token Index: 404