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

Dataset: Open Web Text

Neuron 1766 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: 4.7184. Min Range: -4.7184

Max Act: 4.7184. Min Act: -0.1698

Data Index: 8107639 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 4.7184. Min Range: -4.7184

Max Act: 4.6195. Min Act: -0.1698

Data Index: 1779204 (Open Web Text)

Max Activating Token Index: 37

Text #2

Max Range: 4.7184. Min Range: -4.7184

Max Act: 4.5288. Min Act: -0.1695

Data Index: 5687893 (Open Web Text)

Max Activating Token Index: 66

Text #3

Max Range: 4.7184. Min Range: -4.7184

Max Act: 4.4772. Min Act: -0.1700

Data Index: 3295174 (Open Web Text)

Max Activating Token Index: 18

Text #4

Max Range: 4.7184. Min Range: -4.7184

Max Act: 4.4608. Min Act: -0.1700

Data Index: 8349877 (Open Web Text)

Max Activating Token Index: 17

Text #5

Max Range: 4.7184. Min Range: -4.7184

Max Act: 4.4648. Min Act: -0.1699

Data Index: 2917524 (Open Web Text)

Max Activating Token Index: 160

Text #6

Max Range: 4.7184. Min Range: -4.7184

Max Act: 4.4703. Min Act: -0.1700

Data Index: 2167046 (Open Web Text)

Max Activating Token Index: 304

Text #7

Max Range: 4.7184. Min Range: -4.7184

Max Act: 4.4668. Min Act: -0.1700

Data Index: 4753465 (Open Web Text)

Max Activating Token Index: 334

Text #8

Max Range: 4.7184. Min Range: -4.7184

Max Act: 4.4701. Min Act: -0.1700

Data Index: 6966970 (Open Web Text)

Max Activating Token Index: 259

Text #9

Max Range: 4.7184. Min Range: -4.7184

Max Act: 4.4861. Min Act: -0.1700

Data Index: 5645862 (Open Web Text)

Max Activating Token Index: 126

Text #10

Max Range: 4.7184. Min Range: -4.7184

Max Act: 4.4329. Min Act: -0.1700

Data Index: 7925696 (Open Web Text)

Max Activating Token Index: 328

Text #11

Max Range: 4.7184. Min Range: -4.7184

Max Act: 4.4295. Min Act: -0.1691

Data Index: 4160286 (Open Web Text)

Max Activating Token Index: 436

Text #12

Max Range: 4.7184. Min Range: -4.7184

Max Act: 4.4213. Min Act: -0.1700

Data Index: 7966563 (Open Web Text)

Max Activating Token Index: 60

Text #13

Max Range: 4.7184. Min Range: -4.7184

Max Act: 4.4300. Min Act: -0.1698

Data Index: 4046508 (Open Web Text)

Max Activating Token Index: 189

Text #14

Max Range: 4.7184. Min Range: -4.7184

Max Act: 4.4319. Min Act: -0.1700

Data Index: 2657200 (Open Web Text)

Max Activating Token Index: 14

Text #15

Max Range: 4.7184. Min Range: -4.7184

Max Act: 4.4399. Min Act: -0.1698

Data Index: 4931984 (Open Web Text)

Max Activating Token Index: 251

Text #16

Max Range: 4.7184. Min Range: -4.7184

Max Act: 4.4438. Min Act: -0.1700

Data Index: 5190910 (Open Web Text)

Max Activating Token Index: 233

Text #17

Max Range: 4.7184. Min Range: -4.7184

Max Act: 4.4473. Min Act: -0.1700

Data Index: 8420454 (Open Web Text)

Max Activating Token Index: 278

Text #18

Max Range: 4.7184. Min Range: -4.7184

Max Act: 4.4358. Min Act: -0.1700

Data Index: 1247312 (Open Web Text)

Max Activating Token Index: 22

Text #19

Max Range: 4.7184. Min Range: -4.7184

Max Act: 4.3867. Min Act: -0.1695

Data Index: 380977 (Open Web Text)

Max Activating Token Index: 243