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

Dataset: Open Web Text

Neuron 3057 in Layer 2

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: 3.3134. Min Range: -3.3134

Max Act: 3.3134. Min Act: -0.1700

Data Index: 7181311 (Open Web Text)

Max Activating Token Index: 835

Text #1

Max Range: 3.3134. Min Range: -3.3134

Max Act: 3.3072. Min Act: -0.1700

Data Index: 8738273 (Open Web Text)

Max Activating Token Index: 133

Text #2

Max Range: 3.3134. Min Range: -3.3134

Max Act: 3.3006. Min Act: -0.1700

Data Index: 4286546 (Open Web Text)

Max Activating Token Index: 787

Text #3

Max Range: 3.3134. Min Range: -3.3134

Max Act: 3.2823. Min Act: -0.1700

Data Index: 1049643 (Open Web Text)

Max Activating Token Index: 147

Text #4

Max Range: 3.3134. Min Range: -3.3134

Max Act: 3.2590. Min Act: -0.1700

Data Index: 6642460 (Open Web Text)

Max Activating Token Index: 314

Text #5

Max Range: 3.3134. Min Range: -3.3134

Max Act: 3.2729. Min Act: -0.1700

Data Index: 3941171 (Open Web Text)

Max Activating Token Index: 262

Text #6

Max Range: 3.3134. Min Range: -3.3134

Max Act: 3.2246. Min Act: -0.1700

Data Index: 556826 (Open Web Text)

Max Activating Token Index: 878

Text #7

Max Range: 3.3134. Min Range: -3.3134

Max Act: 3.2019. Min Act: -0.1700

Data Index: 5812660 (Open Web Text)

Max Activating Token Index: 381

Text #8

Max Range: 3.3134. Min Range: -3.3134

Max Act: 3.1779. Min Act: -0.1700

Data Index: 6253222 (Open Web Text)

Max Activating Token Index: 322

Text #9

Max Range: 3.3134. Min Range: -3.3134

Max Act: 3.1679. Min Act: -0.1700

Data Index: 668590 (Open Web Text)

Max Activating Token Index: 573

Text #10

Max Range: 3.3134. Min Range: -3.3134

Max Act: 3.1734. Min Act: -0.1700

Data Index: 971955 (Open Web Text)

Max Activating Token Index: 810

Text #11

Max Range: 3.3134. Min Range: -3.3134

Max Act: 3.1441. Min Act: -0.1700

Data Index: 2200830 (Open Web Text)

Max Activating Token Index: 590

Text #12

Max Range: 3.3134. Min Range: -3.3134

Max Act: 3.1378. Min Act: -0.1700

Data Index: 2786051 (Open Web Text)

Max Activating Token Index: 742

Text #13

Max Range: 3.3134. Min Range: -3.3134

Max Act: 3.1326. Min Act: -0.1700

Data Index: 3539555 (Open Web Text)

Max Activating Token Index: 663

Text #14

Max Range: 3.3134. Min Range: -3.3134

Max Act: 3.1491. Min Act: -0.1700

Data Index: 6695071 (Open Web Text)

Max Activating Token Index: 273

Text #15

Max Range: 3.3134. Min Range: -3.3134

Max Act: 3.1372. Min Act: -0.1700

Data Index: 4595287 (Open Web Text)

Max Activating Token Index: 619

Text #16

Max Range: 3.3134. Min Range: -3.3134

Max Act: 3.1365. Min Act: -0.1700

Data Index: 3063647 (Open Web Text)

Max Activating Token Index: 12

Text #17

Max Range: 3.3134. Min Range: -3.3134

Max Act: 3.1370. Min Act: -0.1700

Data Index: 8664327 (Open Web Text)

Max Activating Token Index: 86

Text #18

Max Range: 3.3134. Min Range: -3.3134

Max Act: 3.1383. Min Act: -0.1700

Data Index: 7405901 (Open Web Text)

Max Activating Token Index: 853

Text #19

Max Range: 3.3134. Min Range: -3.3134

Max Act: 3.1170. Min Act: -0.1700

Data Index: 4796409 (Open Web Text)

Max Activating Token Index: 808