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

Dataset: Open Web Text

Neuron 2679 in Layer 2

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: 4.1224. Min Range: -4.1224

Max Act: 4.1178. Min Act: -0.1700

Data Index: 1352695 (Open Web Text)

Max Activating Token Index: 282

Text #1

Max Range: 4.1224. Min Range: -4.1224

Max Act: 4.0954. Min Act: -0.1700

Data Index: 2433008 (Open Web Text)

Max Activating Token Index: 945

Text #2

Max Range: 4.1224. Min Range: -4.1224

Max Act: 4.1224. Min Act: -0.1700

Data Index: 796135 (Open Web Text)

Max Activating Token Index: 1009

Text #3

Max Range: 4.1224. Min Range: -4.1224

Max Act: 4.0767. Min Act: -0.1700

Data Index: 7715466 (Open Web Text)

Max Activating Token Index: 87

Text #4

Max Range: 4.1224. Min Range: -4.1224

Max Act: 4.0575. Min Act: -0.1700

Data Index: 3102580 (Open Web Text)

Max Activating Token Index: 332

Text #5

Max Range: 4.1224. Min Range: -4.1224

Max Act: 4.0423. Min Act: -0.1700

Data Index: 5812367 (Open Web Text)

Max Activating Token Index: 682

Text #6

Max Range: 4.1224. Min Range: -4.1224

Max Act: 4.0517. Min Act: -0.1700

Data Index: 6908509 (Open Web Text)

Max Activating Token Index: 388

Text #7

Max Range: 4.1224. Min Range: -4.1224

Max Act: 4.0625. Min Act: -0.1700

Data Index: 796136 (Open Web Text)

Max Activating Token Index: 61

Text #8

Max Range: 4.1224. Min Range: -4.1224

Max Act: 4.0147. Min Act: -0.1700

Data Index: 7038761 (Open Web Text)

Max Activating Token Index: 649

Text #9

Max Range: 4.1224. Min Range: -4.1224

Max Act: 4.0020. Min Act: -0.1700

Data Index: 458710 (Open Web Text)

Max Activating Token Index: 538

Text #10

Max Range: 4.1224. Min Range: -4.1224

Max Act: 4.0009. Min Act: -0.1700

Data Index: 3937928 (Open Web Text)

Max Activating Token Index: 792

Text #11

Max Range: 4.1224. Min Range: -4.1224

Max Act: 3.9714. Min Act: -0.1700

Data Index: 3674034 (Open Web Text)

Max Activating Token Index: 1018

Text #12

Max Range: 4.1224. Min Range: -4.1224

Max Act: 3.9965. Min Act: -0.1700

Data Index: 3271098 (Open Web Text)

Max Activating Token Index: 239

Text #13

Max Range: 4.1224. Min Range: -4.1224

Max Act: 4.0140. Min Act: -0.1700

Data Index: 5591136 (Open Web Text)

Max Activating Token Index: 430

Text #14

Max Range: 4.1224. Min Range: -4.1224

Max Act: 3.9817. Min Act: -0.1700

Data Index: 4381939 (Open Web Text)

Max Activating Token Index: 909

Text #15

Max Range: 4.1224. Min Range: -4.1224

Max Act: 3.9600. Min Act: -0.1700

Data Index: 827998 (Open Web Text)

Max Activating Token Index: 334

Text #16

Max Range: 4.1224. Min Range: -4.1224

Max Act: 3.9478. Min Act: -0.1700

Data Index: 3010451 (Open Web Text)

Max Activating Token Index: 413

Text #17

Max Range: 4.1224. Min Range: -4.1224

Max Act: 3.9412. Min Act: -0.1700

Data Index: 5125223 (Open Web Text)

Max Activating Token Index: 474

Text #18

Max Range: 4.1224. Min Range: -4.1224

Max Act: 3.9564. Min Act: -0.1700

Data Index: 37505 (Open Web Text)

Max Activating Token Index: 658

Text #19

Max Range: 4.1224. Min Range: -4.1224

Max Act: 3.9628. Min Act: -0.1700

Data Index: 3810809 (Open Web Text)

Max Activating Token Index: 543