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

Dataset: Open Web Text

Neuron 2465 in Layer 0

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: 4.3716. Min Range: -4.3716

Max Act: 4.3595. Min Act: -0.1700

Data Index: 6645465 (Open Web Text)

Max Activating Token Index: 269

Text #1

Max Range: 4.3716. Min Range: -4.3716

Max Act: 4.3716. Min Act: -0.1700

Data Index: 2233414 (Open Web Text)

Max Activating Token Index: 761

Text #2

Max Range: 4.3716. Min Range: -4.3716

Max Act: 4.2986. Min Act: -0.1700

Data Index: 2233442 (Open Web Text)

Max Activating Token Index: 566

Text #3

Max Range: 4.3716. Min Range: -4.3716

Max Act: 4.3095. Min Act: -0.1700

Data Index: 2233412 (Open Web Text)

Max Activating Token Index: 713

Text #4

Max Range: 4.3716. Min Range: -4.3716

Max Act: 4.3061. Min Act: -0.1700

Data Index: 2233409 (Open Web Text)

Max Activating Token Index: 265

Text #5

Max Range: 4.3716. Min Range: -4.3716

Max Act: 4.2927. Min Act: -0.1700

Data Index: 2233419 (Open Web Text)

Max Activating Token Index: 806

Text #6

Max Range: 4.3716. Min Range: -4.3716

Max Act: 4.3070. Min Act: -0.1698

Data Index: 2233436 (Open Web Text)

Max Activating Token Index: 368

Text #7

Max Range: 4.3716. Min Range: -4.3716

Max Act: 4.3159. Min Act: -0.1700

Data Index: 2233415 (Open Web Text)

Max Activating Token Index: 730

Text #8

Max Range: 4.3716. Min Range: -4.3716

Max Act: 4.3034. Min Act: -0.1700

Data Index: 2233418 (Open Web Text)

Max Activating Token Index: 747

Text #9

Max Range: 4.3716. Min Range: -4.3716

Max Act: 4.2971. Min Act: -0.1700

Data Index: 2233408 (Open Web Text)

Max Activating Token Index: 771

Text #10

Max Range: 4.3716. Min Range: -4.3716

Max Act: 4.2649. Min Act: -0.1693

Data Index: 2233446 (Open Web Text)

Max Activating Token Index: 810

Text #11

Max Range: 4.3716. Min Range: -4.3716

Max Act: 4.2541. Min Act: -0.1700

Data Index: 1619316 (Open Web Text)

Max Activating Token Index: 55

Text #12

Max Range: 4.3716. Min Range: -4.3716

Max Act: 4.2554. Min Act: -0.1696

Data Index: 2233438 (Open Web Text)

Max Activating Token Index: 392

Text #13

Max Range: 4.3716. Min Range: -4.3716

Max Act: 4.2742. Min Act: -0.1699

Data Index: 2233441 (Open Web Text)

Max Activating Token Index: 565

Text #14

Max Range: 4.3716. Min Range: -4.3716

Max Act: 4.2663. Min Act: -0.1700

Data Index: 2233407 (Open Web Text)

Max Activating Token Index: 426

Text #15

Max Range: 4.3716. Min Range: -4.3716

Max Act: 4.2507. Min Act: -0.1700

Data Index: 2233413 (Open Web Text)

Max Activating Token Index: 217

Text #16

Max Range: 4.3716. Min Range: -4.3716

Max Act: 4.2829. Min Act: -0.1699

Data Index: 2233437 (Open Web Text)

Max Activating Token Index: 393

Text #17

Max Range: 4.3716. Min Range: -4.3716

Max Act: 4.2420. Min Act: -0.1700

Data Index: 2233406 (Open Web Text)

Max Activating Token Index: 942

Text #18

Max Range: 4.3716. Min Range: -4.3716

Max Act: 4.2244. Min Act: -0.1700

Data Index: 2233420 (Open Web Text)

Max Activating Token Index: 815

Text #19

Max Range: 4.3716. Min Range: -4.3716

Max Act: 4.2262. Min Act: -0.1698

Data Index: 2233432 (Open Web Text)

Max Activating Token Index: 819