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

Dataset: Open Web Text

Neuron 2691 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: 4.7149. Min Range: -4.7149

Max Act: 4.7149. Min Act: -0.1700

Data Index: 5691410 (Open Web Text)

Max Activating Token Index: 891

Text #1

Max Range: 4.7149. Min Range: -4.7149

Max Act: 4.7038. Min Act: -0.1700

Data Index: 606237 (Open Web Text)

Max Activating Token Index: 49

Text #2

Max Range: 4.7149. Min Range: -4.7149

Max Act: 4.6128. Min Act: -0.1700

Data Index: 506974 (Open Web Text)

Max Activating Token Index: 542

Text #3

Max Range: 4.7149. Min Range: -4.7149

Max Act: 4.5294. Min Act: -0.1700

Data Index: 5815188 (Open Web Text)

Max Activating Token Index: 283

Text #4

Max Range: 4.7149. Min Range: -4.7149

Max Act: 4.5288. Min Act: -0.1700

Data Index: 2378299 (Open Web Text)

Max Activating Token Index: 17

Text #5

Max Range: 4.7149. Min Range: -4.7149

Max Act: 4.5665. Min Act: -0.1700

Data Index: 3607378 (Open Web Text)

Max Activating Token Index: 851

Text #6

Max Range: 4.7149. Min Range: -4.7149

Max Act: 4.5194. Min Act: -0.1700

Data Index: 852038 (Open Web Text)

Max Activating Token Index: 671

Text #7

Max Range: 4.7149. Min Range: -4.7149

Max Act: 4.4977. Min Act: -0.1700

Data Index: 4440920 (Open Web Text)

Max Activating Token Index: 223

Text #8

Max Range: 4.7149. Min Range: -4.7149

Max Act: 4.4825. Min Act: -0.1700

Data Index: 3758741 (Open Web Text)

Max Activating Token Index: 379

Text #9

Max Range: 4.7149. Min Range: -4.7149

Max Act: 4.4857. Min Act: -0.1700

Data Index: 949482 (Open Web Text)

Max Activating Token Index: 284

Text #10

Max Range: 4.7149. Min Range: -4.7149

Max Act: 4.4626. Min Act: -0.1700

Data Index: 4135511 (Open Web Text)

Max Activating Token Index: 27

Text #11

Max Range: 4.7149. Min Range: -4.7149

Max Act: 4.4717. Min Act: -0.1700

Data Index: 5179895 (Open Web Text)

Max Activating Token Index: 430

Text #12

Max Range: 4.7149. Min Range: -4.7149

Max Act: 4.4683. Min Act: -0.1700

Data Index: 3912047 (Open Web Text)

Max Activating Token Index: 426

Text #13

Max Range: 4.7149. Min Range: -4.7149

Max Act: 4.4863. Min Act: -0.1700

Data Index: 5310885 (Open Web Text)

Max Activating Token Index: 265

Text #14

Max Range: 4.7149. Min Range: -4.7149

Max Act: 4.4686. Min Act: -0.1700

Data Index: 1154214 (Open Web Text)

Max Activating Token Index: 332

Text #15

Max Range: 4.7149. Min Range: -4.7149

Max Act: 4.4144. Min Act: -0.1700

Data Index: 7369503 (Open Web Text)

Max Activating Token Index: 53

Text #16

Max Range: 4.7149. Min Range: -4.7149

Max Act: 4.4288. Min Act: -0.1700

Data Index: 8816803 (Open Web Text)

Max Activating Token Index: 341

Text #17

Max Range: 4.7149. Min Range: -4.7149

Max Act: 4.4210. Min Act: -0.1700

Data Index: 1061202 (Open Web Text)

Max Activating Token Index: 859

Text #18

Max Range: 4.7149. Min Range: -4.7149

Max Act: 4.4493. Min Act: -0.1700

Data Index: 3805800 (Open Web Text)

Max Activating Token Index: 908

Text #19

Max Range: 4.7149. Min Range: -4.7149

Max Act: 4.4092. Min Act: -0.1700

Data Index: 5188238 (Open Web Text)

Max Activating Token Index: 903