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

Dataset: Open Web Text

Neuron 1812 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: 3.3373. Min Range: -3.3373

Max Act: 3.3373. Min Act: -0.1700

Data Index: 4973060 (Open Web Text)

Max Activating Token Index: 833

Text #1

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.3082. Min Act: -0.1700

Data Index: 7059794 (Open Web Text)

Max Activating Token Index: 409

Text #2

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.2928. Min Act: -0.1700

Data Index: 674494 (Open Web Text)

Max Activating Token Index: 409

Text #3

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.2613. Min Act: -0.1700

Data Index: 4628975 (Open Web Text)

Max Activating Token Index: 501

Text #4

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.2239. Min Act: -0.1700

Data Index: 4067395 (Open Web Text)

Max Activating Token Index: 323

Text #5

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.2336. Min Act: -0.1700

Data Index: 6550138 (Open Web Text)

Max Activating Token Index: 255

Text #6

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.2221. Min Act: -0.1700

Data Index: 6827874 (Open Web Text)

Max Activating Token Index: 527

Text #7

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.2225. Min Act: -0.1700

Data Index: 341628 (Open Web Text)

Max Activating Token Index: 233

Text #8

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.2348. Min Act: -0.1700

Data Index: 3601115 (Open Web Text)

Max Activating Token Index: 412

Text #9

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.2044. Min Act: -0.1700

Data Index: 5383112 (Open Web Text)

Max Activating Token Index: 880

Text #10

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.2167. Min Act: -0.1700

Data Index: 8220099 (Open Web Text)

Max Activating Token Index: 572

Text #11

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.1777. Min Act: -0.1700

Data Index: 8335843 (Open Web Text)

Max Activating Token Index: 217

Text #12

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.1704. Min Act: -0.1700

Data Index: 1500830 (Open Web Text)

Max Activating Token Index: 783

Text #13

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.2165. Min Act: -0.1700

Data Index: 5466093 (Open Web Text)

Max Activating Token Index: 742

Text #14

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.1883. Min Act: -0.1700

Data Index: 4345285 (Open Web Text)

Max Activating Token Index: 343

Text #15

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.1753. Min Act: -0.1700

Data Index: 4062158 (Open Web Text)

Max Activating Token Index: 558

Text #16

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.1555. Min Act: -0.1700

Data Index: 407154 (Open Web Text)

Max Activating Token Index: 398

Text #17

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.1435. Min Act: -0.1700

Data Index: 2094484 (Open Web Text)

Max Activating Token Index: 786

Text #18

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.1320. Min Act: -0.1700

Data Index: 8546697 (Open Web Text)

Max Activating Token Index: 796

Text #19

Max Range: 3.3373. Min Range: -3.3373

Max Act: 3.1462. Min Act: -0.1700

Data Index: 3743641 (Open Web Text)

Max Activating Token Index: 856