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

Dataset: Open Web Text

Neuron 707 in Layer 3

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: 3.6674. Min Range: -3.6674

Max Act: 3.6674. Min Act: -0.1700

Data Index: 2561580 (Open Web Text)

Max Activating Token Index: 932

Text #1

Max Range: 3.6674. Min Range: -3.6674

Max Act: 3.5322. Min Act: -0.1700

Data Index: 6406223 (Open Web Text)

Max Activating Token Index: 677

Text #2

Max Range: 3.6674. Min Range: -3.6674

Max Act: 3.5418. Min Act: -0.1700

Data Index: 871115 (Open Web Text)

Max Activating Token Index: 441

Text #3

Max Range: 3.6674. Min Range: -3.6674

Max Act: 3.5124. Min Act: -0.1700

Data Index: 419473 (Open Web Text)

Max Activating Token Index: 500

Text #4

Max Range: 3.6674. Min Range: -3.6674

Max Act: 3.5234. Min Act: -0.1700

Data Index: 2561568 (Open Web Text)

Max Activating Token Index: 696

Text #5

Max Range: 3.6674. Min Range: -3.6674

Max Act: 3.4111. Min Act: -0.1700

Data Index: 3635570 (Open Web Text)

Max Activating Token Index: 765

Text #6

Max Range: 3.6674. Min Range: -3.6674

Max Act: 3.4963. Min Act: -0.1700

Data Index: 6519084 (Open Web Text)

Max Activating Token Index: 160

Text #7

Max Range: 3.6674. Min Range: -3.6674

Max Act: 3.5287. Min Act: -0.1700

Data Index: 2864811 (Open Web Text)

Max Activating Token Index: 340

Text #8

Max Range: 3.6674. Min Range: -3.6674

Max Act: 3.4675. Min Act: -0.1700

Data Index: 6554964 (Open Web Text)

Max Activating Token Index: 156

Text #9

Max Range: 3.6674. Min Range: -3.6674

Max Act: 3.5109. Min Act: -0.1700

Data Index: 5695107 (Open Web Text)

Max Activating Token Index: 365

Text #10

Max Range: 3.6674. Min Range: -3.6674

Max Act: 3.4935. Min Act: -0.1700

Data Index: 2967979 (Open Web Text)

Max Activating Token Index: 450

Text #11

Max Range: 3.6674. Min Range: -3.6674

Max Act: 3.5087. Min Act: -0.1700

Data Index: 5054855 (Open Web Text)

Max Activating Token Index: 374

Text #12

Max Range: 3.6674. Min Range: -3.6674

Max Act: 3.4672. Min Act: -0.1700

Data Index: 1955971 (Open Web Text)

Max Activating Token Index: 505

Text #13

Max Range: 3.6674. Min Range: -3.6674

Max Act: 3.4839. Min Act: -0.1700

Data Index: 2295482 (Open Web Text)

Max Activating Token Index: 889

Text #14

Max Range: 3.6674. Min Range: -3.6674

Max Act: 3.4526. Min Act: -0.1700

Data Index: 1949802 (Open Web Text)

Max Activating Token Index: 442

Text #15

Max Range: 3.6674. Min Range: -3.6674

Max Act: 3.4128. Min Act: -0.1700

Data Index: 3832909 (Open Web Text)

Max Activating Token Index: 454

Text #16

Max Range: 3.6674. Min Range: -3.6674

Max Act: 3.4716. Min Act: -0.1700

Data Index: 7098143 (Open Web Text)

Max Activating Token Index: 270

Text #17

Max Range: 3.6674. Min Range: -3.6674

Max Act: 3.4454. Min Act: -0.1700

Data Index: 8290217 (Open Web Text)

Max Activating Token Index: 797

Text #18

Max Range: 3.6674. Min Range: -3.6674

Max Act: 3.4095. Min Act: -0.1700

Data Index: 1767617 (Open Web Text)

Max Activating Token Index: 380

Text #19

Max Range: 3.6674. Min Range: -3.6674

Max Act: 3.5106. Min Act: -0.1700

Data Index: 1639719 (Open Web Text)

Max Activating Token Index: 667