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

Dataset: Open Web Text

Neuron 1331 in Layer 4

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: 3.0369. Min Range: -3.0369

Max Act: 3.0369. Min Act: -0.1700

Data Index: 3964749 (Open Web Text)

Max Activating Token Index: 1006

Text #1

Max Range: 3.0369. Min Range: -3.0369

Max Act: 3.0264. Min Act: -0.1700

Data Index: 6969238 (Open Web Text)

Max Activating Token Index: 997

Text #2

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.9833. Min Act: -0.1700

Data Index: 7590774 (Open Web Text)

Max Activating Token Index: 808

Text #3

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.9756. Min Act: -0.1700

Data Index: 2629155 (Open Web Text)

Max Activating Token Index: 644

Text #4

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.9763. Min Act: -0.1700

Data Index: 883533 (Open Web Text)

Max Activating Token Index: 219

Text #5

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.9543. Min Act: -0.1700

Data Index: 4511251 (Open Web Text)

Max Activating Token Index: 790

Text #6

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.8965. Min Act: -0.1700

Data Index: 4767838 (Open Web Text)

Max Activating Token Index: 564

Text #7

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.9089. Min Act: -0.1700

Data Index: 2015444 (Open Web Text)

Max Activating Token Index: 644

Text #8

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.8938. Min Act: -0.1700

Data Index: 1680459 (Open Web Text)

Max Activating Token Index: 974

Text #9

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.8992. Min Act: -0.1700

Data Index: 6633646 (Open Web Text)

Max Activating Token Index: 838

Text #10

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.8702. Min Act: -0.1700

Data Index: 1228868 (Open Web Text)

Max Activating Token Index: 257

Text #11

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.9142. Min Act: -0.1700

Data Index: 2496112 (Open Web Text)

Max Activating Token Index: 899

Text #12

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.8360. Min Act: -0.1700

Data Index: 2006373 (Open Web Text)

Max Activating Token Index: 352

Text #13

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.8311. Min Act: -0.1700

Data Index: 2606597 (Open Web Text)

Max Activating Token Index: 165

Text #14

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.8561. Min Act: -0.1700

Data Index: 3827592 (Open Web Text)

Max Activating Token Index: 959

Text #15

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.8527. Min Act: -0.1700

Data Index: 4211056 (Open Web Text)

Max Activating Token Index: 181

Text #16

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.8585. Min Act: -0.1700

Data Index: 6536250 (Open Web Text)

Max Activating Token Index: 796

Text #17

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.8251. Min Act: -0.1700

Data Index: 6410123 (Open Web Text)

Max Activating Token Index: 335

Text #18

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.8518. Min Act: -0.1700

Data Index: 617946 (Open Web Text)

Max Activating Token Index: 424

Text #19

Max Range: 3.0369. Min Range: -3.0369

Max Act: 2.8100. Min Act: -0.1700

Data Index: 5026109 (Open Web Text)

Max Activating Token Index: 123