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

Dataset: Open Web Text

Neuron 322 in Layer 1

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: 1.8810. Min Range: -1.8810

Max Act: 1.8810. Min Act: -0.1700

Data Index: 1992206 (Open Web Text)

Max Activating Token Index: 206

Text #1

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.8563. Min Act: -0.1700

Data Index: 3038951 (Open Web Text)

Max Activating Token Index: 779

Text #2

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.8308. Min Act: -0.1700

Data Index: 2796208 (Open Web Text)

Max Activating Token Index: 887

Text #3

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.8250. Min Act: -0.1700

Data Index: 7373165 (Open Web Text)

Max Activating Token Index: 494

Text #4

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.8096. Min Act: -0.1700

Data Index: 6911914 (Open Web Text)

Max Activating Token Index: 468

Text #5

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.7948. Min Act: -0.1700

Data Index: 8224345 (Open Web Text)

Max Activating Token Index: 60

Text #6

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.8056. Min Act: -0.1699

Data Index: 7666499 (Open Web Text)

Max Activating Token Index: 425

Text #7

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.7967. Min Act: -0.1700

Data Index: 1623688 (Open Web Text)

Max Activating Token Index: 969

Text #8

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.7959. Min Act: -0.1700

Data Index: 3991324 (Open Web Text)

Max Activating Token Index: 876

Text #9

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.7913. Min Act: -0.1700

Data Index: 337588 (Open Web Text)

Max Activating Token Index: 313

Text #10

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.7845. Min Act: -0.1700

Data Index: 5608310 (Open Web Text)

Max Activating Token Index: 556

Text #11

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.7831. Min Act: -0.1700

Data Index: 7260784 (Open Web Text)

Max Activating Token Index: 119

Text #12

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.7784. Min Act: -0.1700

Data Index: 8534760 (Open Web Text)

Max Activating Token Index: 267

Text #13

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.7895. Min Act: -0.1700

Data Index: 3061526 (Open Web Text)

Max Activating Token Index: 457

Text #14

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.7842. Min Act: -0.1700

Data Index: 1608601 (Open Web Text)

Max Activating Token Index: 532

Text #15

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.7797. Min Act: -0.1699

Data Index: 7560074 (Open Web Text)

Max Activating Token Index: 567

Text #16

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.7780. Min Act: -0.1700

Data Index: 6418312 (Open Web Text)

Max Activating Token Index: 508

Text #17

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.7739. Min Act: -0.1700

Data Index: 8755452 (Open Web Text)

Max Activating Token Index: 122

Text #18

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.7697. Min Act: -0.1700

Data Index: 6732803 (Open Web Text)

Max Activating Token Index: 385

Text #19

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.7689. Min Act: -0.1700

Data Index: 621080 (Open Web Text)

Max Activating Token Index: 371