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

Dataset: Open Web Text

Neuron 2971 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: 4.2029. Min Range: -4.2029

Max Act: 4.2029. Min Act: -0.1700

Data Index: 7327844 (Open Web Text)

Max Activating Token Index: 127

Text #1

Max Range: 4.2029. Min Range: -4.2029

Max Act: 4.1706. Min Act: -0.1700

Data Index: 1164197 (Open Web Text)

Max Activating Token Index: 660

Text #2

Max Range: 4.2029. Min Range: -4.2029

Max Act: 4.1287. Min Act: -0.1700

Data Index: 1188974 (Open Web Text)

Max Activating Token Index: 205

Text #3

Max Range: 4.2029. Min Range: -4.2029

Max Act: 4.1153. Min Act: -0.1700

Data Index: 2221619 (Open Web Text)

Max Activating Token Index: 649

Text #4

Max Range: 4.2029. Min Range: -4.2029

Max Act: 4.0348. Min Act: -0.1700

Data Index: 2364279 (Open Web Text)

Max Activating Token Index: 62

Text #5

Max Range: 4.2029. Min Range: -4.2029

Max Act: 4.0329. Min Act: -0.1700

Data Index: 7549981 (Open Web Text)

Max Activating Token Index: 935

Text #6

Max Range: 4.2029. Min Range: -4.2029

Max Act: 4.0244. Min Act: -0.1700

Data Index: 6823203 (Open Web Text)

Max Activating Token Index: 990

Text #7

Max Range: 4.2029. Min Range: -4.2029

Max Act: 3.9749. Min Act: -0.1700

Data Index: 2504795 (Open Web Text)

Max Activating Token Index: 986

Text #8

Max Range: 4.2029. Min Range: -4.2029

Max Act: 3.9720. Min Act: -0.1700

Data Index: 3068155 (Open Web Text)

Max Activating Token Index: 115

Text #9

Max Range: 4.2029. Min Range: -4.2029

Max Act: 3.9987. Min Act: -0.1700

Data Index: 934519 (Open Web Text)

Max Activating Token Index: 886

Text #10

Max Range: 4.2029. Min Range: -4.2029

Max Act: 3.9846. Min Act: -0.1700

Data Index: 3335282 (Open Web Text)

Max Activating Token Index: 798

Text #11

Max Range: 4.2029. Min Range: -4.2029

Max Act: 3.9340. Min Act: -0.1700

Data Index: 8617206 (Open Web Text)

Max Activating Token Index: 980

Text #12

Max Range: 4.2029. Min Range: -4.2029

Max Act: 3.9516. Min Act: -0.1700

Data Index: 5300885 (Open Web Text)

Max Activating Token Index: 994

Text #13

Max Range: 4.2029. Min Range: -4.2029

Max Act: 3.9232. Min Act: -0.1700

Data Index: 5779535 (Open Web Text)

Max Activating Token Index: 55

Text #14

Max Range: 4.2029. Min Range: -4.2029

Max Act: 3.9643. Min Act: -0.1700

Data Index: 1196064 (Open Web Text)

Max Activating Token Index: 536

Text #15

Max Range: 4.2029. Min Range: -4.2029

Max Act: 3.9644. Min Act: -0.1700

Data Index: 430231 (Open Web Text)

Max Activating Token Index: 623

Text #16

Max Range: 4.2029. Min Range: -4.2029

Max Act: 3.9856. Min Act: -0.1700

Data Index: 5193730 (Open Web Text)

Max Activating Token Index: 484

Text #17

Max Range: 4.2029. Min Range: -4.2029

Max Act: 3.9217. Min Act: -0.1700

Data Index: 7060648 (Open Web Text)

Max Activating Token Index: 436

Text #18

Max Range: 4.2029. Min Range: -4.2029

Max Act: 3.9541. Min Act: -0.1700

Data Index: 1354055 (Open Web Text)

Max Activating Token Index: 324

Text #19

Max Range: 4.2029. Min Range: -4.2029

Max Act: 3.9258. Min Act: -0.1700

Data Index: 2503221 (Open Web Text)

Max Activating Token Index: 715