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

Dataset: Open Web Text

Neuron 2742 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: 4.8676. Min Range: -4.8676

Max Act: 4.8676. Min Act: -0.1700

Data Index: 1208513 (Open Web Text)

Max Activating Token Index: 919

Text #1

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.6899. Min Act: -0.1700

Data Index: 7226690 (Open Web Text)

Max Activating Token Index: 167

Text #2

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.5594. Min Act: -0.1700

Data Index: 5320457 (Open Web Text)

Max Activating Token Index: 380

Text #3

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.5987. Min Act: -0.1700

Data Index: 2602058 (Open Web Text)

Max Activating Token Index: 251

Text #4

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.5751. Min Act: -0.1700

Data Index: 5098135 (Open Web Text)

Max Activating Token Index: 631

Text #5

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.5314. Min Act: -0.1700

Data Index: 7086639 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.4936. Min Act: -0.1700

Data Index: 7894253 (Open Web Text)

Max Activating Token Index: 509

Text #7

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.4254. Min Act: -0.1700

Data Index: 6942690 (Open Web Text)

Max Activating Token Index: 148

Text #8

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.4400. Min Act: -0.1700

Data Index: 6877857 (Open Web Text)

Max Activating Token Index: 468

Text #9

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.4151. Min Act: -0.1700

Data Index: 7054307 (Open Web Text)

Max Activating Token Index: 395

Text #10

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.4060. Min Act: -0.1700

Data Index: 6755701 (Open Web Text)

Max Activating Token Index: 639

Text #11

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.4219. Min Act: -0.1700

Data Index: 5222146 (Open Web Text)

Max Activating Token Index: 744

Text #12

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.4287. Min Act: -0.1700

Data Index: 818007 (Open Web Text)

Max Activating Token Index: 140

Text #13

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.4267. Min Act: -0.1700

Data Index: 4640424 (Open Web Text)

Max Activating Token Index: 813

Text #14

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.4080. Min Act: -0.1700

Data Index: 6749105 (Open Web Text)

Max Activating Token Index: 544

Text #15

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.4249. Min Act: -0.1700

Data Index: 692580 (Open Web Text)

Max Activating Token Index: 707

Text #16

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.4293. Min Act: -0.1700

Data Index: 1102839 (Open Web Text)

Max Activating Token Index: 516

Text #17

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.3976. Min Act: -0.1700

Data Index: 2755537 (Open Web Text)

Max Activating Token Index: 757

Text #18

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.3873. Min Act: -0.1700

Data Index: 1300552 (Open Web Text)

Max Activating Token Index: 628

Text #19

Max Range: 4.8676. Min Range: -4.8676

Max Act: 4.3487. Min Act: -0.1700

Data Index: 5186793 (Open Web Text)

Max Activating Token Index: 1018