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

Dataset: Open Web Text

Neuron 1667 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: 3.8248. Min Range: -3.8248

Max Act: 3.7976. Min Act: -0.1700

Data Index: 2223498 (Open Web Text)

Max Activating Token Index: 208

Text #1

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.8248. Min Act: -0.1700

Data Index: 4784404 (Open Web Text)

Max Activating Token Index: 408

Text #2

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.7334. Min Act: -0.1700

Data Index: 7595275 (Open Web Text)

Max Activating Token Index: 1001

Text #3

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.6797. Min Act: -0.1700

Data Index: 7357765 (Open Web Text)

Max Activating Token Index: 1009

Text #4

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.6919. Min Act: -0.1700

Data Index: 4199926 (Open Web Text)

Max Activating Token Index: 780

Text #5

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.6968. Min Act: -0.1700

Data Index: 3975173 (Open Web Text)

Max Activating Token Index: 342

Text #6

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.6696. Min Act: -0.1700

Data Index: 4387193 (Open Web Text)

Max Activating Token Index: 598

Text #7

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.6172. Min Act: -0.1700

Data Index: 97164 (Open Web Text)

Max Activating Token Index: 178

Text #8

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.5952. Min Act: -0.1700

Data Index: 1670533 (Open Web Text)

Max Activating Token Index: 689

Text #9

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.6419. Min Act: -0.1700

Data Index: 4942994 (Open Web Text)

Max Activating Token Index: 821

Text #10

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.6257. Min Act: -0.1700

Data Index: 4380237 (Open Web Text)

Max Activating Token Index: 621

Text #11

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.6067. Min Act: -0.1700

Data Index: 7271811 (Open Web Text)

Max Activating Token Index: 605

Text #12

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.6020. Min Act: -0.1700

Data Index: 8280300 (Open Web Text)

Max Activating Token Index: 277

Text #13

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.5815. Min Act: -0.1700

Data Index: 241565 (Open Web Text)

Max Activating Token Index: 632

Text #14

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.5781. Min Act: -0.1700

Data Index: 4160895 (Open Web Text)

Max Activating Token Index: 218

Text #15

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.5912. Min Act: -0.1700

Data Index: 6939262 (Open Web Text)

Max Activating Token Index: 49

Text #16

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.6016. Min Act: -0.1700

Data Index: 1209999 (Open Web Text)

Max Activating Token Index: 862

Text #17

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.5754. Min Act: -0.1700

Data Index: 5342147 (Open Web Text)

Max Activating Token Index: 326

Text #18

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.5595. Min Act: -0.1700

Data Index: 5124835 (Open Web Text)

Max Activating Token Index: 214

Text #19

Max Range: 3.8248. Min Range: -3.8248

Max Act: 3.5298. Min Act: -0.1700

Data Index: 5030128 (Open Web Text)

Max Activating Token Index: 762