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

Dataset: Open Web Text

Neuron 2152 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: 3.8368. Min Range: -3.8368

Max Act: 3.8368. Min Act: -0.1700

Data Index: 709928 (Open Web Text)

Max Activating Token Index: 987

Text #1

Max Range: 3.8368. Min Range: -3.8368

Max Act: 3.8220. Min Act: -0.1700

Data Index: 3614952 (Open Web Text)

Max Activating Token Index: 990

Text #2

Max Range: 3.8368. Min Range: -3.8368

Max Act: 3.6890. Min Act: -0.1700

Data Index: 3930899 (Open Web Text)

Max Activating Token Index: 726

Text #3

Max Range: 3.8368. Min Range: -3.8368

Max Act: 3.6866. Min Act: -0.1700

Data Index: 7445532 (Open Web Text)

Max Activating Token Index: 872

Text #4

Max Range: 3.8368. Min Range: -3.8368

Max Act: 3.6324. Min Act: -0.1700

Data Index: 2895547 (Open Web Text)

Max Activating Token Index: 464

Text #5

Max Range: 3.8368. Min Range: -3.8368

Max Act: 3.7060. Min Act: -0.1700

Data Index: 2204341 (Open Web Text)

Max Activating Token Index: 316

Text #6

Max Range: 3.8368. Min Range: -3.8368

Max Act: 3.6074. Min Act: -0.1700

Data Index: 8802422 (Open Web Text)

Max Activating Token Index: 636

Text #7

Max Range: 3.8368. Min Range: -3.8368

Max Act: 3.5278. Min Act: -0.1700

Data Index: 6041071 (Open Web Text)

Max Activating Token Index: 721

Text #8

Max Range: 3.8368. Min Range: -3.8368

Max Act: 3.5143. Min Act: -0.1700

Data Index: 4192163 (Open Web Text)

Max Activating Token Index: 200

Text #9

Max Range: 3.8368. Min Range: -3.8368

Max Act: 3.5177. Min Act: -0.1700

Data Index: 1223118 (Open Web Text)

Max Activating Token Index: 406

Text #10

Max Range: 3.8368. Min Range: -3.8368

Max Act: 3.4754. Min Act: -0.1700

Data Index: 2120114 (Open Web Text)

Max Activating Token Index: 272

Text #11

Max Range: 3.8368. Min Range: -3.8368

Max Act: 3.3995. Min Act: -0.1700

Data Index: 2142568 (Open Web Text)

Max Activating Token Index: 1007

Text #12

Max Range: 3.8368. Min Range: -3.8368

Max Act: 3.4763. Min Act: -0.1700

Data Index: 4057227 (Open Web Text)

Max Activating Token Index: 720

Text #13

Max Range: 3.8368. Min Range: -3.8368

Max Act: 3.4301. Min Act: -0.1700

Data Index: 1874315 (Open Web Text)

Max Activating Token Index: 966

Text #14

Max Range: 3.8368. Min Range: -3.8368

Max Act: 3.4561. Min Act: -0.1700

Data Index: 4987557 (Open Web Text)

Max Activating Token Index: 460

Text #15

Max Range: 3.8368. Min Range: -3.8368

Max Act: 3.4029. Min Act: -0.1700

Data Index: 1304725 (Open Web Text)

Max Activating Token Index: 755

Text #16

Max Range: 3.8368. Min Range: -3.8368

Max Act: 3.4345. Min Act: -0.1700

Data Index: 1970284 (Open Web Text)

Max Activating Token Index: 313

Text #17

Max Range: 3.8368. Min Range: -3.8368

Max Act: 3.4101. Min Act: -0.1700

Data Index: 7662059 (Open Web Text)

Max Activating Token Index: 51

Text #18

Max Range: 3.8368. Min Range: -3.8368

Max Act: 3.4262. Min Act: -0.1700

Data Index: 2341096 (Open Web Text)

Max Activating Token Index: 841

Text #19

Max Range: 3.8368. Min Range: -3.8368

Max Act: 3.3935. Min Act: -0.1700

Data Index: 1859119 (Open Web Text)

Max Activating Token Index: 536