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

Dataset: Open Web Text

Neuron 2060 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: 4.6128. Min Range: -4.6128

Max Act: 4.6128. Min Act: -0.1700

Data Index: 3214078 (Open Web Text)

Max Activating Token Index: 383

Text #1

Max Range: 4.6128. Min Range: -4.6128

Max Act: 4.5037. Min Act: -0.1700

Data Index: 2263263 (Open Web Text)

Max Activating Token Index: 171

Text #2

Max Range: 4.6128. Min Range: -4.6128

Max Act: 4.5618. Min Act: -0.1700

Data Index: 5398437 (Open Web Text)

Max Activating Token Index: 20

Text #3

Max Range: 4.6128. Min Range: -4.6128

Max Act: 4.5208. Min Act: -0.1700

Data Index: 8032455 (Open Web Text)

Max Activating Token Index: 575

Text #4

Max Range: 4.6128. Min Range: -4.6128

Max Act: 4.5859. Min Act: -0.1700

Data Index: 4099000 (Open Web Text)

Max Activating Token Index: 636

Text #5

Max Range: 4.6128. Min Range: -4.6128

Max Act: 4.5340. Min Act: -0.1700

Data Index: 2930319 (Open Web Text)

Max Activating Token Index: 256

Text #6

Max Range: 4.6128. Min Range: -4.6128

Max Act: 4.4600. Min Act: -0.1700

Data Index: 7508501 (Open Web Text)

Max Activating Token Index: 191

Text #7

Max Range: 4.6128. Min Range: -4.6128

Max Act: 4.5075. Min Act: -0.1700

Data Index: 925588 (Open Web Text)

Max Activating Token Index: 56

Text #8

Max Range: 4.6128. Min Range: -4.6128

Max Act: 4.4861. Min Act: -0.1700

Data Index: 6790017 (Open Web Text)

Max Activating Token Index: 1017

Text #9

Max Range: 4.6128. Min Range: -4.6128

Max Act: 4.4888. Min Act: -0.1700

Data Index: 4822255 (Open Web Text)

Max Activating Token Index: 16

Text #10

Max Range: 4.6128. Min Range: -4.6128

Max Act: 4.4430. Min Act: -0.1700

Data Index: 6847130 (Open Web Text)

Max Activating Token Index: 578

Text #11

Max Range: 4.6128. Min Range: -4.6128

Max Act: 4.4465. Min Act: -0.1700

Data Index: 6396742 (Open Web Text)

Max Activating Token Index: 528

Text #12

Max Range: 4.6128. Min Range: -4.6128

Max Act: 4.5217. Min Act: -0.1700

Data Index: 1474479 (Open Web Text)

Max Activating Token Index: 754

Text #13

Max Range: 4.6128. Min Range: -4.6128

Max Act: 4.5475. Min Act: -0.1700

Data Index: 6160590 (Open Web Text)

Max Activating Token Index: 631

Text #14

Max Range: 4.6128. Min Range: -4.6128

Max Act: 4.5166. Min Act: -0.1700

Data Index: 8597333 (Open Web Text)

Max Activating Token Index: 766

Text #15

Max Range: 4.6128. Min Range: -4.6128

Max Act: 4.4933. Min Act: -0.1700

Data Index: 3699134 (Open Web Text)

Max Activating Token Index: 400

Text #16

Max Range: 4.6128. Min Range: -4.6128

Max Act: 4.4864. Min Act: -0.1700

Data Index: 1678986 (Open Web Text)

Max Activating Token Index: 376

Text #17

Max Range: 4.6128. Min Range: -4.6128

Max Act: 4.4939. Min Act: -0.1700

Data Index: 5804860 (Open Web Text)

Max Activating Token Index: 643

Text #18

Max Range: 4.6128. Min Range: -4.6128

Max Act: 4.5181. Min Act: -0.1700

Data Index: 3915446 (Open Web Text)

Max Activating Token Index: 887

Text #19

Max Range: 4.6128. Min Range: -4.6128

Max Act: 4.4769. Min Act: -0.1700

Data Index: 5329207 (Open Web Text)

Max Activating Token Index: 41