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

Dataset: Open Web Text

Neuron 1888 in Layer 5

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: 4.6361. Min Range: -4.6361

Max Act: 4.6361. Min Act: -0.1599

Data Index: 4388456 (Open Web Text)

Max Activating Token Index: 1

Text #1

Max Range: 4.6361. Min Range: -4.6361

Max Act: 4.6361. Min Act: -0.1406

Data Index: 7642968 (Open Web Text)

Max Activating Token Index: 1

Text #2

Max Range: 4.6361. Min Range: -4.6361

Max Act: 4.6361. Min Act: -0.1574

Data Index: 6894105 (Open Web Text)

Max Activating Token Index: 1

Text #3

Max Range: 4.6361. Min Range: -4.6361

Max Act: 4.6361. Min Act: -0.0874

Data Index: 570059 (Open Web Text)

Max Activating Token Index: 1

Text #4

Max Range: 4.6361. Min Range: -4.6361

Max Act: 4.6361. Min Act: -0.1056

Data Index: 331595 (Open Web Text)

Max Activating Token Index: 1

Text #5

Max Range: 4.6361. Min Range: -4.6361

Max Act: 4.6361. Min Act: -0.1663

Data Index: 2393017 (Open Web Text)

Max Activating Token Index: 1

Text #6

Max Range: 4.6361. Min Range: -4.6361

Max Act: 4.6361. Min Act: -0.1059

Data Index: 6594872 (Open Web Text)

Max Activating Token Index: 1

Text #7

Max Range: 4.6361. Min Range: -4.6361

Max Act: 4.6361. Min Act: -0.0947

Data Index: 2454794 (Open Web Text)

Max Activating Token Index: 1

Text #8

Max Range: 4.6361. Min Range: -4.6361

Max Act: 4.6361. Min Act: -0.1550

Data Index: 5192241 (Open Web Text)

Max Activating Token Index: 1

Text #9

Max Range: 4.6361. Min Range: -4.6361

Max Act: 4.6361. Min Act: -0.0191

Data Index: 4593767 (Open Web Text)

Max Activating Token Index: 1

Text #10

Max Range: 4.6361. Min Range: -4.6361

Max Act: 4.6361. Min Act: 0.0203

Data Index: 2591600 (Open Web Text)

Max Activating Token Index: 1

Text #11

Max Range: 4.6361. Min Range: -4.6361

Max Act: 4.6361. Min Act: -0.1002

Data Index: 4336412 (Open Web Text)

Max Activating Token Index: 1

Text #12

Max Range: 4.6361. Min Range: -4.6361

Max Act: 4.6361. Min Act: -0.0040

Data Index: 4209617 (Open Web Text)

Max Activating Token Index: 1

Text #13

Max Range: 4.6361. Min Range: -4.6361

Max Act: 4.6361. Min Act: 0.1643

Data Index: 4128800 (Open Web Text)

Max Activating Token Index: 1

Text #14

Max Range: 4.6361. Min Range: -4.6361

Max Act: 4.6361. Min Act: -0.1664

Data Index: 2192173 (Open Web Text)

Max Activating Token Index: 1

Text #15

Max Range: 4.6361. Min Range: -4.6361

Max Act: 4.6361. Min Act: -0.1386

Data Index: 4048994 (Open Web Text)

Max Activating Token Index: 1

Text #16

Max Range: 4.6361. Min Range: -4.6361

Max Act: 4.6361. Min Act: -0.1579

Data Index: 3589227 (Open Web Text)

Max Activating Token Index: 1

Text #17

Max Range: 4.6361. Min Range: -4.6361

Max Act: 4.6361. Min Act: -0.1699

Data Index: 831718 (Open Web Text)

Max Activating Token Index: 1

Text #18

Max Range: 4.6361. Min Range: -4.6361

Max Act: 4.6361. Min Act: -0.0998

Data Index: 2856838 (Open Web Text)

Max Activating Token Index: 1

Text #19

Max Range: 4.6361. Min Range: -4.6361

Max Act: 4.6361. Min Act: -0.1693

Data Index: 2706766 (Open Web Text)

Max Activating Token Index: 1