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

Dataset: Open Web Text

Neuron 926 in Layer 1

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: 1.4713. Min Range: -1.4713

Max Act: 1.4620. Min Act: -0.1700

Data Index: 6211326 (Open Web Text)

Max Activating Token Index: 438

Text #1

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.4713. Min Act: -0.1698

Data Index: 5082135 (Open Web Text)

Max Activating Token Index: 727

Text #2

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.4560. Min Act: -0.1695

Data Index: 7176691 (Open Web Text)

Max Activating Token Index: 773

Text #3

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.4638. Min Act: -0.1700

Data Index: 3516911 (Open Web Text)

Max Activating Token Index: 450

Text #4

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.4468. Min Act: -0.1699

Data Index: 8361285 (Open Web Text)

Max Activating Token Index: 678

Text #5

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.4509. Min Act: -0.1700

Data Index: 5173289 (Open Web Text)

Max Activating Token Index: 813

Text #6

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.4545. Min Act: -0.1700

Data Index: 4638880 (Open Web Text)

Max Activating Token Index: 35

Text #7

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.4429. Min Act: -0.1685

Data Index: 4520407 (Open Web Text)

Max Activating Token Index: 483

Text #8

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.4251. Min Act: -0.1657

Data Index: 6758773 (Open Web Text)

Max Activating Token Index: 126

Text #9

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.4291. Min Act: -0.1699

Data Index: 3216857 (Open Web Text)

Max Activating Token Index: 828

Text #10

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.4195. Min Act: -0.1700

Data Index: 4739181 (Open Web Text)

Max Activating Token Index: 458

Text #11

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.4220. Min Act: -0.1699

Data Index: 920119 (Open Web Text)

Max Activating Token Index: 684

Text #12

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.4158. Min Act: -0.1698

Data Index: 5100433 (Open Web Text)

Max Activating Token Index: 549

Text #13

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.4056. Min Act: -0.1699

Data Index: 8719319 (Open Web Text)

Max Activating Token Index: 304

Text #14

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.4038. Min Act: -0.1700

Data Index: 4569166 (Open Web Text)

Max Activating Token Index: 172

Text #15

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.4039. Min Act: -0.1680

Data Index: 833587 (Open Web Text)

Max Activating Token Index: 259

Text #16

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.4035. Min Act: -0.1700

Data Index: 2473601 (Open Web Text)

Max Activating Token Index: 917

Text #17

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.4049. Min Act: -0.1700

Data Index: 2511030 (Open Web Text)

Max Activating Token Index: 1019

Text #18

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.4028. Min Act: -0.1700

Data Index: 5936677 (Open Web Text)

Max Activating Token Index: 199

Text #19

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.3959. Min Act: -0.1700

Data Index: 1174868 (Open Web Text)

Max Activating Token Index: 208