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

Dataset: Open Web Text

Neuron 1497 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: 0.7302. Min Range: -0.7302

Max Act: 0.7302. Min Act: -0.1700

Data Index: 8154884 (Open Web Text)

Max Activating Token Index: 210

Text #1

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6998. Min Act: -0.1700

Data Index: 6972004 (Open Web Text)

Max Activating Token Index: 212

Text #2

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6931. Min Act: -0.1700

Data Index: 5330619 (Open Web Text)

Max Activating Token Index: 32

Text #3

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6824. Min Act: -0.1700

Data Index: 1555379 (Open Web Text)

Max Activating Token Index: 201

Text #4

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6820. Min Act: -0.1700

Data Index: 5574040 (Open Web Text)

Max Activating Token Index: 220

Text #5

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6774. Min Act: -0.1700

Data Index: 5502553 (Open Web Text)

Max Activating Token Index: 213

Text #6

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6769. Min Act: -0.1700

Data Index: 2468197 (Open Web Text)

Max Activating Token Index: 223

Text #7

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6665. Min Act: -0.1700

Data Index: 5502551 (Open Web Text)

Max Activating Token Index: 203

Text #8

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6677. Min Act: -0.1700

Data Index: 2873646 (Open Web Text)

Max Activating Token Index: 26

Text #9

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6609. Min Act: -0.1700

Data Index: 7902769 (Open Web Text)

Max Activating Token Index: 214

Text #10

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6615. Min Act: -0.1700

Data Index: 1789084 (Open Web Text)

Max Activating Token Index: 26

Text #11

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6603. Min Act: -0.1700

Data Index: 2426209 (Open Web Text)

Max Activating Token Index: 206

Text #12

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6524. Min Act: -0.1700

Data Index: 4162624 (Open Web Text)

Max Activating Token Index: 1

Text #13

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6524. Min Act: -0.1700

Data Index: 1502423 (Open Web Text)

Max Activating Token Index: 1

Text #14

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6524. Min Act: -0.1700

Data Index: 239142 (Open Web Text)

Max Activating Token Index: 1

Text #15

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6524. Min Act: -0.1700

Data Index: 1850124 (Open Web Text)

Max Activating Token Index: 1

Text #16

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6524. Min Act: -0.1700

Data Index: 3719325 (Open Web Text)

Max Activating Token Index: 1

Text #17

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6524. Min Act: -0.1697

Data Index: 475381 (Open Web Text)

Max Activating Token Index: 1

Text #18

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6524. Min Act: -0.1700

Data Index: 1833348 (Open Web Text)

Max Activating Token Index: 1

Text #19

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6524. Min Act: -0.1700

Data Index: 1767439 (Open Web Text)

Max Activating Token Index: 1