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

Dataset: Open Web Text

Neuron 605 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: 3.6397. Min Range: -3.6397

Max Act: 3.6397. Min Act: -0.1700

Data Index: 7520291 (Open Web Text)

Max Activating Token Index: 1016

Text #1

Max Range: 3.6397. Min Range: -3.6397

Max Act: 3.6075. Min Act: -0.1700

Data Index: 4936578 (Open Web Text)

Max Activating Token Index: 124

Text #2

Max Range: 3.6397. Min Range: -3.6397

Max Act: 3.6159. Min Act: -0.1700

Data Index: 6414125 (Open Web Text)

Max Activating Token Index: 916

Text #3

Max Range: 3.6397. Min Range: -3.6397

Max Act: 3.6100. Min Act: -0.1700

Data Index: 7137427 (Open Web Text)

Max Activating Token Index: 960

Text #4

Max Range: 3.6397. Min Range: -3.6397

Max Act: 3.6195. Min Act: -0.1700

Data Index: 2680279 (Open Web Text)

Max Activating Token Index: 499

Text #5

Max Range: 3.6397. Min Range: -3.6397

Max Act: 3.5956. Min Act: -0.1700

Data Index: 7320472 (Open Web Text)

Max Activating Token Index: 620

Text #6

Max Range: 3.6397. Min Range: -3.6397

Max Act: 3.6051. Min Act: -0.1700

Data Index: 7191970 (Open Web Text)

Max Activating Token Index: 545

Text #7

Max Range: 3.6397. Min Range: -3.6397

Max Act: 3.5828. Min Act: -0.1700

Data Index: 202243 (Open Web Text)

Max Activating Token Index: 109

Text #8

Max Range: 3.6397. Min Range: -3.6397

Max Act: 3.5663. Min Act: -0.1700

Data Index: 6111457 (Open Web Text)

Max Activating Token Index: 477

Text #9

Max Range: 3.6397. Min Range: -3.6397

Max Act: 3.5525. Min Act: -0.1700

Data Index: 4003070 (Open Web Text)

Max Activating Token Index: 690

Text #10

Max Range: 3.6397. Min Range: -3.6397

Max Act: 3.5552. Min Act: -0.1700

Data Index: 3926225 (Open Web Text)

Max Activating Token Index: 311

Text #11

Max Range: 3.6397. Min Range: -3.6397

Max Act: 3.5259. Min Act: -0.1700

Data Index: 1009004 (Open Web Text)

Max Activating Token Index: 176

Text #12

Max Range: 3.6397. Min Range: -3.6397

Max Act: 3.5535. Min Act: -0.1700

Data Index: 3699651 (Open Web Text)

Max Activating Token Index: 905

Text #13

Max Range: 3.6397. Min Range: -3.6397

Max Act: 3.5284. Min Act: -0.1700

Data Index: 3596945 (Open Web Text)

Max Activating Token Index: 227

Text #14

Max Range: 3.6397. Min Range: -3.6397

Max Act: 3.5176. Min Act: -0.1700

Data Index: 1643916 (Open Web Text)

Max Activating Token Index: 442

Text #15

Max Range: 3.6397. Min Range: -3.6397

Max Act: 3.4902. Min Act: -0.1700

Data Index: 8237765 (Open Web Text)

Max Activating Token Index: 985

Text #16

Max Range: 3.6397. Min Range: -3.6397

Max Act: 3.4972. Min Act: -0.1700

Data Index: 7539575 (Open Web Text)

Max Activating Token Index: 980

Text #17

Max Range: 3.6397. Min Range: -3.6397

Max Act: 3.5151. Min Act: -0.1700

Data Index: 2761974 (Open Web Text)

Max Activating Token Index: 529

Text #18

Max Range: 3.6397. Min Range: -3.6397

Max Act: 3.4785. Min Act: -0.1700

Data Index: 3897188 (Open Web Text)

Max Activating Token Index: 326

Text #19

Max Range: 3.6397. Min Range: -3.6397

Max Act: 3.5017. Min Act: -0.1700

Data Index: 7284272 (Open Web Text)

Max Activating Token Index: 405