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

Dataset: Open Web Text

Neuron 1400 in Layer 6

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: 4.8042. Min Range: -4.8042

Max Act: 4.8042. Min Act: -0.1700

Data Index: 4263214 (Open Web Text)

Max Activating Token Index: 451

Text #1

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.6775. Min Act: -0.1700

Data Index: 7839093 (Open Web Text)

Max Activating Token Index: 637

Text #2

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.6660. Min Act: -0.1700

Data Index: 4579683 (Open Web Text)

Max Activating Token Index: 432

Text #3

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.6971. Min Act: -0.1700

Data Index: 792649 (Open Web Text)

Max Activating Token Index: 76

Text #4

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.6993. Min Act: -0.1700

Data Index: 7404157 (Open Web Text)

Max Activating Token Index: 993

Text #5

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.5923. Min Act: -0.1700

Data Index: 8065034 (Open Web Text)

Max Activating Token Index: 56

Text #6

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.5943. Min Act: -0.1700

Data Index: 3725511 (Open Web Text)

Max Activating Token Index: 240

Text #7

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.6062. Min Act: -0.1700

Data Index: 2574594 (Open Web Text)

Max Activating Token Index: 112

Text #8

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.5611. Min Act: -0.1700

Data Index: 5684183 (Open Web Text)

Max Activating Token Index: 476

Text #9

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.5745. Min Act: -0.1700

Data Index: 2997301 (Open Web Text)

Max Activating Token Index: 150

Text #10

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.5340. Min Act: -0.1700

Data Index: 8337624 (Open Web Text)

Max Activating Token Index: 207

Text #11

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.5666. Min Act: -0.1700

Data Index: 2654701 (Open Web Text)

Max Activating Token Index: 665

Text #12

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.5106. Min Act: -0.1700

Data Index: 1908169 (Open Web Text)

Max Activating Token Index: 136

Text #13

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.5449. Min Act: -0.1700

Data Index: 328769 (Open Web Text)

Max Activating Token Index: 909

Text #14

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.5526. Min Act: -0.1700

Data Index: 7615311 (Open Web Text)

Max Activating Token Index: 797

Text #15

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.5536. Min Act: -0.1700

Data Index: 3637723 (Open Web Text)

Max Activating Token Index: 106

Text #16

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.5268. Min Act: -0.1700

Data Index: 2223569 (Open Web Text)

Max Activating Token Index: 447

Text #17

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.5404. Min Act: -0.1700

Data Index: 222247 (Open Web Text)

Max Activating Token Index: 417

Text #18

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.4739. Min Act: -0.1700

Data Index: 4647206 (Open Web Text)

Max Activating Token Index: 110

Text #19

Max Range: 4.8042. Min Range: -4.8042

Max Act: 4.5327. Min Act: -0.1700

Data Index: 3768047 (Open Web Text)

Max Activating Token Index: 938