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

Dataset: Open Web Text

Neuron 1742 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: 3.3676. Min Range: -3.3676

Max Act: 3.3676. Min Act: -0.1700

Data Index: 3555610 (Open Web Text)

Max Activating Token Index: 395

Text #1

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.2788. Min Act: -0.1700

Data Index: 7781605 (Open Web Text)

Max Activating Token Index: 716

Text #2

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.2240. Min Act: -0.1700

Data Index: 6105124 (Open Web Text)

Max Activating Token Index: 491

Text #3

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.2161. Min Act: -0.1700

Data Index: 8426699 (Open Web Text)

Max Activating Token Index: 37

Text #4

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.1317. Min Act: -0.1700

Data Index: 8397125 (Open Web Text)

Max Activating Token Index: 694

Text #5

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.0840. Min Act: -0.1700

Data Index: 893348 (Open Web Text)

Max Activating Token Index: 708

Text #6

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.1193. Min Act: -0.1700

Data Index: 5395175 (Open Web Text)

Max Activating Token Index: 163

Text #7

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.1309. Min Act: -0.1700

Data Index: 6597974 (Open Web Text)

Max Activating Token Index: 210

Text #8

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.1055. Min Act: -0.1700

Data Index: 6400277 (Open Web Text)

Max Activating Token Index: 580

Text #9

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.0934. Min Act: -0.1700

Data Index: 4379886 (Open Web Text)

Max Activating Token Index: 740

Text #10

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.1158. Min Act: -0.1700

Data Index: 2130344 (Open Web Text)

Max Activating Token Index: 895

Text #11

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.0981. Min Act: -0.1700

Data Index: 8812871 (Open Web Text)

Max Activating Token Index: 339

Text #12

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.0700. Min Act: -0.1700

Data Index: 1852306 (Open Web Text)

Max Activating Token Index: 894

Text #13

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.0739. Min Act: -0.1700

Data Index: 6977143 (Open Web Text)

Max Activating Token Index: 712

Text #14

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.0224. Min Act: -0.1700

Data Index: 5389122 (Open Web Text)

Max Activating Token Index: 521

Text #15

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.0117. Min Act: -0.1700

Data Index: 889977 (Open Web Text)

Max Activating Token Index: 624

Text #16

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.0384. Min Act: -0.1700

Data Index: 1329588 (Open Web Text)

Max Activating Token Index: 696

Text #17

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.0663. Min Act: -0.1700

Data Index: 514089 (Open Web Text)

Max Activating Token Index: 852

Text #18

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.0757. Min Act: -0.1700

Data Index: 309463 (Open Web Text)

Max Activating Token Index: 306

Text #19

Max Range: 3.3676. Min Range: -3.3676

Max Act: 3.0402. Min Act: -0.1700

Data Index: 3339524 (Open Web Text)

Max Activating Token Index: 546