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

Dataset: Open Web Text

Neuron 983 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: 1.7918. Min Range: -1.7918

Max Act: 1.7918. Min Act: -0.1700

Data Index: 5176507 (Open Web Text)

Max Activating Token Index: 91

Text #1

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.7677. Min Act: -0.1700

Data Index: 4256848 (Open Web Text)

Max Activating Token Index: 86

Text #2

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.7595. Min Act: -0.1700

Data Index: 1677197 (Open Web Text)

Max Activating Token Index: 199

Text #3

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.7567. Min Act: -0.1700

Data Index: 739624 (Open Web Text)

Max Activating Token Index: 570

Text #4

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.7608. Min Act: -0.1700

Data Index: 2006978 (Open Web Text)

Max Activating Token Index: 886

Text #5

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.7509. Min Act: -0.1700

Data Index: 2056531 (Open Web Text)

Max Activating Token Index: 636

Text #6

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.7364. Min Act: -0.1700

Data Index: 5645436 (Open Web Text)

Max Activating Token Index: 972

Text #7

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.7410. Min Act: -0.1700

Data Index: 4468602 (Open Web Text)

Max Activating Token Index: 784

Text #8

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.7430. Min Act: -0.1700

Data Index: 6250430 (Open Web Text)

Max Activating Token Index: 226

Text #9

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.7379. Min Act: -0.1700

Data Index: 7630211 (Open Web Text)

Max Activating Token Index: 500

Text #10

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.7235. Min Act: -0.1700

Data Index: 8544958 (Open Web Text)

Max Activating Token Index: 1011

Text #11

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.7365. Min Act: -0.1700

Data Index: 1773503 (Open Web Text)

Max Activating Token Index: 194

Text #12

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.7274. Min Act: -0.1700

Data Index: 1438829 (Open Web Text)

Max Activating Token Index: 91

Text #13

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.7238. Min Act: -0.1700

Data Index: 2566967 (Open Web Text)

Max Activating Token Index: 401

Text #14

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.7273. Min Act: -0.1700

Data Index: 5987568 (Open Web Text)

Max Activating Token Index: 965

Text #15

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.7121. Min Act: -0.1700

Data Index: 7474773 (Open Web Text)

Max Activating Token Index: 96

Text #16

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.7127. Min Act: -0.1690

Data Index: 3135083 (Open Web Text)

Max Activating Token Index: 124

Text #17

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.7052. Min Act: -0.1700

Data Index: 4800728 (Open Web Text)

Max Activating Token Index: 873

Text #18

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.7041. Min Act: -0.1700

Data Index: 532493 (Open Web Text)

Max Activating Token Index: 456

Text #19

Max Range: 1.7918. Min Range: -1.7918

Max Act: 1.7084. Min Act: -0.1700

Data Index: 4953930 (Open Web Text)

Max Activating Token Index: 462