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

Dataset: Open Web Text

Neuron 599 in Layer 0

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: 2.9243. Min Range: -2.9243

Max Act: 2.9243. Min Act: -0.1700

Data Index: 7967711 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.9075. Min Act: -0.1700

Data Index: 6236204 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.8882. Min Act: -0.1700

Data Index: 1623079 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.8769. Min Act: -0.1700

Data Index: 8281111 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.8715. Min Act: -0.1700

Data Index: 828391 (Open Web Text)

Max Activating Token Index: 918

Text #5

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.8712. Min Act: -0.1700

Data Index: 3821286 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.8638. Min Act: -0.1700

Data Index: 1590400 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.8591. Min Act: -0.1700

Data Index: 2295230 (Open Web Text)

Max Activating Token Index: 334

Text #8

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.8651. Min Act: -0.1700

Data Index: 7670084 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.8353. Min Act: -0.1700

Data Index: 3421772 (Open Web Text)

Max Activating Token Index: 787

Text #10

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.8387. Min Act: -0.1700

Data Index: 8305686 (Open Web Text)

Max Activating Token Index: 664

Text #11

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.8341. Min Act: -0.1700

Data Index: 3828862 (Open Web Text)

Max Activating Token Index: 330

Text #12

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.8255. Min Act: -0.1700

Data Index: 2218179 (Open Web Text)

Max Activating Token Index: 928

Text #13

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.8248. Min Act: -0.1700

Data Index: 7066876 (Open Web Text)

Max Activating Token Index: 927

Text #14

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.8317. Min Act: -0.1700

Data Index: 5153489 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.8172. Min Act: -0.1700

Data Index: 2295232 (Open Web Text)

Max Activating Token Index: 337

Text #16

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.8186. Min Act: -0.1700

Data Index: 1013346 (Open Web Text)

Max Activating Token Index: 13

Text #17

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.8302. Min Act: -0.1700

Data Index: 4738140 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.8119. Min Act: -0.1700

Data Index: 2460020 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.9243. Min Range: -2.9243

Max Act: 2.8115. Min Act: -0.1700

Data Index: 317689 (Open Web Text)

Max Activating Token Index: 10