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

Dataset: Open Web Text

Neuron 1341 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: 5.2234. Min Range: -5.2234

Max Act: 5.2234. Min Act: -0.1700

Data Index: 1289879 (Open Web Text)

Max Activating Token Index: 435

Text #1

Max Range: 5.2234. Min Range: -5.2234

Max Act: 5.0510. Min Act: -0.1700

Data Index: 4633475 (Open Web Text)

Max Activating Token Index: 587

Text #2

Max Range: 5.2234. Min Range: -5.2234

Max Act: 4.9131. Min Act: -0.1700

Data Index: 7372854 (Open Web Text)

Max Activating Token Index: 180

Text #3

Max Range: 5.2234. Min Range: -5.2234

Max Act: 4.9451. Min Act: -0.1700

Data Index: 5869158 (Open Web Text)

Max Activating Token Index: 104

Text #4

Max Range: 5.2234. Min Range: -5.2234

Max Act: 4.8651. Min Act: -0.1700

Data Index: 5930390 (Open Web Text)

Max Activating Token Index: 648

Text #5

Max Range: 5.2234. Min Range: -5.2234

Max Act: 4.9224. Min Act: -0.1700

Data Index: 1285618 (Open Web Text)

Max Activating Token Index: 798

Text #6

Max Range: 5.2234. Min Range: -5.2234

Max Act: 4.8208. Min Act: -0.1700

Data Index: 8101866 (Open Web Text)

Max Activating Token Index: 192

Text #7

Max Range: 5.2234. Min Range: -5.2234

Max Act: 4.8529. Min Act: -0.1700

Data Index: 2463713 (Open Web Text)

Max Activating Token Index: 390

Text #8

Max Range: 5.2234. Min Range: -5.2234

Max Act: 4.8369. Min Act: -0.1700

Data Index: 1905083 (Open Web Text)

Max Activating Token Index: 164

Text #9

Max Range: 5.2234. Min Range: -5.2234

Max Act: 4.8301. Min Act: -0.1700

Data Index: 6470104 (Open Web Text)

Max Activating Token Index: 270

Text #10

Max Range: 5.2234. Min Range: -5.2234

Max Act: 4.8497. Min Act: -0.1700

Data Index: 8475664 (Open Web Text)

Max Activating Token Index: 35

Text #11

Max Range: 5.2234. Min Range: -5.2234

Max Act: 4.8360. Min Act: -0.1700

Data Index: 8672302 (Open Web Text)

Max Activating Token Index: 271

Text #12

Max Range: 5.2234. Min Range: -5.2234

Max Act: 4.8048. Min Act: -0.1700

Data Index: 5206499 (Open Web Text)

Max Activating Token Index: 960

Text #13

Max Range: 5.2234. Min Range: -5.2234

Max Act: 4.7841. Min Act: -0.1700

Data Index: 7672417 (Open Web Text)

Max Activating Token Index: 687

Text #14

Max Range: 5.2234. Min Range: -5.2234

Max Act: 4.7758. Min Act: -0.1700

Data Index: 7008502 (Open Web Text)

Max Activating Token Index: 259

Text #15

Max Range: 5.2234. Min Range: -5.2234

Max Act: 4.7105. Min Act: -0.1700

Data Index: 3156614 (Open Web Text)

Max Activating Token Index: 599

Text #16

Max Range: 5.2234. Min Range: -5.2234

Max Act: 4.7789. Min Act: -0.1700

Data Index: 7577889 (Open Web Text)

Max Activating Token Index: 556

Text #17

Max Range: 5.2234. Min Range: -5.2234

Max Act: 4.7081. Min Act: -0.1700

Data Index: 1847649 (Open Web Text)

Max Activating Token Index: 108

Text #18

Max Range: 5.2234. Min Range: -5.2234

Max Act: 4.7179. Min Act: -0.1700

Data Index: 6076675 (Open Web Text)

Max Activating Token Index: 198

Text #19

Max Range: 5.2234. Min Range: -5.2234

Max Act: 4.6910. Min Act: -0.1700

Data Index: 833274 (Open Web Text)

Max Activating Token Index: 759