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

Dataset: Open Web Text

Neuron 685 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: 1.7315. Min Range: -1.7315

Max Act: 1.7315. Min Act: -0.1700

Data Index: 8215622 (Open Web Text)

Max Activating Token Index: 105

Text #1

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.7097. Min Act: -0.1700

Data Index: 7134361 (Open Web Text)

Max Activating Token Index: 54

Text #2

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.7060. Min Act: -0.1700

Data Index: 6010138 (Open Web Text)

Max Activating Token Index: 616

Text #3

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6940. Min Act: -0.1700

Data Index: 1274681 (Open Web Text)

Max Activating Token Index: 973

Text #4

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6929. Min Act: -0.1700

Data Index: 4432921 (Open Web Text)

Max Activating Token Index: 102

Text #5

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6881. Min Act: -0.1700

Data Index: 6997524 (Open Web Text)

Max Activating Token Index: 80

Text #6

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6928. Min Act: -0.1675

Data Index: 6293444 (Open Web Text)

Max Activating Token Index: 111

Text #7

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6784. Min Act: -0.1699

Data Index: 1494223 (Open Web Text)

Max Activating Token Index: 118

Text #8

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6742. Min Act: -0.1700

Data Index: 1268527 (Open Web Text)

Max Activating Token Index: 767

Text #9

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6770. Min Act: -0.1700

Data Index: 7691737 (Open Web Text)

Max Activating Token Index: 90

Text #10

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6738. Min Act: -0.1700

Data Index: 7341016 (Open Web Text)

Max Activating Token Index: 442

Text #11

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6720. Min Act: -0.1698

Data Index: 8493997 (Open Web Text)

Max Activating Token Index: 54

Text #12

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6695. Min Act: -0.1700

Data Index: 1879948 (Open Web Text)

Max Activating Token Index: 918

Text #13

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6700. Min Act: -0.1700

Data Index: 6898691 (Open Web Text)

Max Activating Token Index: 69

Text #14

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6687. Min Act: -0.1700

Data Index: 626126 (Open Web Text)

Max Activating Token Index: 101

Text #15

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6653. Min Act: -0.1700

Data Index: 211618 (Open Web Text)

Max Activating Token Index: 226

Text #16

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6626. Min Act: -0.1699

Data Index: 1005886 (Open Web Text)

Max Activating Token Index: 544

Text #17

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6507. Min Act: -0.1700

Data Index: 6818554 (Open Web Text)

Max Activating Token Index: 601

Text #18

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6591. Min Act: -0.1700

Data Index: 75905 (Open Web Text)

Max Activating Token Index: 83

Text #19

Max Range: 1.7315. Min Range: -1.7315

Max Act: 1.6593. Min Act: -0.1700

Data Index: 7752547 (Open Web Text)

Max Activating Token Index: 578