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

Dataset: Open Web Text

Neuron 1363 in Layer 6

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: 3.1170. Min Range: -3.1170

Max Act: 3.1170. Min Act: -0.1700

Data Index: 1540120 (Open Web Text)

Max Activating Token Index: 462

Text #1

Max Range: 3.1170. Min Range: -3.1170

Max Act: 3.0666. Min Act: -0.1700

Data Index: 2728016 (Open Web Text)

Max Activating Token Index: 602

Text #2

Max Range: 3.1170. Min Range: -3.1170

Max Act: 3.0304. Min Act: -0.1700

Data Index: 417431 (Open Web Text)

Max Activating Token Index: 964

Text #3

Max Range: 3.1170. Min Range: -3.1170

Max Act: 2.9441. Min Act: -0.1700

Data Index: 991437 (Open Web Text)

Max Activating Token Index: 252

Text #4

Max Range: 3.1170. Min Range: -3.1170

Max Act: 2.9456. Min Act: -0.1700

Data Index: 472724 (Open Web Text)

Max Activating Token Index: 818

Text #5

Max Range: 3.1170. Min Range: -3.1170

Max Act: 2.9340. Min Act: -0.1700

Data Index: 216172 (Open Web Text)

Max Activating Token Index: 1010

Text #6

Max Range: 3.1170. Min Range: -3.1170

Max Act: 2.8994. Min Act: -0.1700

Data Index: 5603798 (Open Web Text)

Max Activating Token Index: 791

Text #7

Max Range: 3.1170. Min Range: -3.1170

Max Act: 2.8479. Min Act: -0.1700

Data Index: 7617604 (Open Web Text)

Max Activating Token Index: 727

Text #8

Max Range: 3.1170. Min Range: -3.1170

Max Act: 2.8692. Min Act: -0.1700

Data Index: 4632617 (Open Web Text)

Max Activating Token Index: 104

Text #9

Max Range: 3.1170. Min Range: -3.1170

Max Act: 2.8494. Min Act: -0.1700

Data Index: 4158066 (Open Web Text)

Max Activating Token Index: 25

Text #10

Max Range: 3.1170. Min Range: -3.1170

Max Act: 2.8523. Min Act: -0.1700

Data Index: 2956159 (Open Web Text)

Max Activating Token Index: 492

Text #11

Max Range: 3.1170. Min Range: -3.1170

Max Act: 2.8379. Min Act: -0.1700

Data Index: 7600136 (Open Web Text)

Max Activating Token Index: 345

Text #12

Max Range: 3.1170. Min Range: -3.1170

Max Act: 2.8509. Min Act: -0.1700

Data Index: 978087 (Open Web Text)

Max Activating Token Index: 330

Text #13

Max Range: 3.1170. Min Range: -3.1170

Max Act: 2.8200. Min Act: -0.1700

Data Index: 926536 (Open Web Text)

Max Activating Token Index: 64

Text #14

Max Range: 3.1170. Min Range: -3.1170

Max Act: 2.8103. Min Act: -0.1700

Data Index: 1218188 (Open Web Text)

Max Activating Token Index: 879

Text #15

Max Range: 3.1170. Min Range: -3.1170

Max Act: 2.8108. Min Act: -0.1700

Data Index: 1541182 (Open Web Text)

Max Activating Token Index: 341

Text #16

Max Range: 3.1170. Min Range: -3.1170

Max Act: 2.8125. Min Act: -0.1700

Data Index: 3853304 (Open Web Text)

Max Activating Token Index: 266

Text #17

Max Range: 3.1170. Min Range: -3.1170

Max Act: 2.7885. Min Act: -0.1700

Data Index: 6945753 (Open Web Text)

Max Activating Token Index: 874

Text #18

Max Range: 3.1170. Min Range: -3.1170

Max Act: 2.8039. Min Act: -0.1700

Data Index: 1238185 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 3.1170. Min Range: -3.1170

Max Act: 2.7949. Min Act: -0.1700

Data Index: 2168298 (Open Web Text)

Max Activating Token Index: 890