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

Dataset: Open Web Text

Neuron 1104 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: 3.0303. Min Range: -3.0303

Max Act: 3.0303. Min Act: -0.1700

Data Index: 5868913 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.8918. Min Act: -0.1700

Data Index: 7971528 (Open Web Text)

Max Activating Token Index: 279

Text #2

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.9184. Min Act: -0.1700

Data Index: 2712009 (Open Web Text)

Max Activating Token Index: 597

Text #3

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.8727. Min Act: -0.1700

Data Index: 3979190 (Open Web Text)

Max Activating Token Index: 261

Text #4

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.8461. Min Act: -0.1700

Data Index: 7719485 (Open Web Text)

Max Activating Token Index: 750

Text #5

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.8871. Min Act: -0.1700

Data Index: 5431185 (Open Web Text)

Max Activating Token Index: 273

Text #6

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.8553. Min Act: -0.1700

Data Index: 4060832 (Open Web Text)

Max Activating Token Index: 481

Text #7

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.8292. Min Act: -0.1700

Data Index: 444637 (Open Web Text)

Max Activating Token Index: 564

Text #8

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.8518. Min Act: -0.1700

Data Index: 5521543 (Open Web Text)

Max Activating Token Index: 333

Text #9

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.8402. Min Act: -0.1700

Data Index: 6261188 (Open Web Text)

Max Activating Token Index: 474

Text #10

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.8145. Min Act: -0.1700

Data Index: 1910770 (Open Web Text)

Max Activating Token Index: 403

Text #11

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.8292. Min Act: -0.1700

Data Index: 5431182 (Open Web Text)

Max Activating Token Index: 366

Text #12

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.8284. Min Act: -0.1700

Data Index: 5597992 (Open Web Text)

Max Activating Token Index: 314

Text #13

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.8148. Min Act: -0.1700

Data Index: 4116520 (Open Web Text)

Max Activating Token Index: 202

Text #14

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.8201. Min Act: -0.1700

Data Index: 3219698 (Open Web Text)

Max Activating Token Index: 803

Text #15

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.8046. Min Act: -0.1700

Data Index: 5431177 (Open Web Text)

Max Activating Token Index: 686

Text #16

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.7875. Min Act: -0.1700

Data Index: 3163621 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.8101. Min Act: -0.1700

Data Index: 5521538 (Open Web Text)

Max Activating Token Index: 973

Text #18

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.8017. Min Act: -0.1700

Data Index: 4408936 (Open Web Text)

Max Activating Token Index: 346

Text #19

Max Range: 3.0303. Min Range: -3.0303

Max Act: 2.8151. Min Act: -0.1700

Data Index: 3157320 (Open Web Text)

Max Activating Token Index: 899