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

Dataset: Open Web Text

Neuron 1562 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: 3.5866. Min Range: -3.5866

Max Act: 3.5866. Min Act: -0.1700

Data Index: 4195871 (Open Web Text)

Max Activating Token Index: 461

Text #1

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.2837. Min Act: -0.1700

Data Index: 8697283 (Open Web Text)

Max Activating Token Index: 970

Text #2

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.2521. Min Act: -0.1700

Data Index: 2030750 (Open Web Text)

Max Activating Token Index: 629

Text #3

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.2247. Min Act: -0.1700

Data Index: 1845684 (Open Web Text)

Max Activating Token Index: 386

Text #4

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.2053. Min Act: -0.1700

Data Index: 2913365 (Open Web Text)

Max Activating Token Index: 1000

Text #5

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.2182. Min Act: -0.1700

Data Index: 5805944 (Open Web Text)

Max Activating Token Index: 245

Text #6

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.1777. Min Act: -0.1700

Data Index: 6467503 (Open Web Text)

Max Activating Token Index: 306

Text #7

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.1923. Min Act: -0.1700

Data Index: 7801886 (Open Web Text)

Max Activating Token Index: 83

Text #8

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.1552. Min Act: -0.1700

Data Index: 3326938 (Open Web Text)

Max Activating Token Index: 313

Text #9

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.1938. Min Act: -0.1700

Data Index: 5641702 (Open Web Text)

Max Activating Token Index: 235

Text #10

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.1769. Min Act: -0.1700

Data Index: 3148887 (Open Web Text)

Max Activating Token Index: 673

Text #11

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.1331. Min Act: -0.1700

Data Index: 1625372 (Open Web Text)

Max Activating Token Index: 536

Text #12

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.1746. Min Act: -0.1700

Data Index: 323037 (Open Web Text)

Max Activating Token Index: 744

Text #13

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.1501. Min Act: -0.1700

Data Index: 200773 (Open Web Text)

Max Activating Token Index: 395

Text #14

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.1242. Min Act: -0.1700

Data Index: 2727698 (Open Web Text)

Max Activating Token Index: 72

Text #15

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.1324. Min Act: -0.1700

Data Index: 8228604 (Open Web Text)

Max Activating Token Index: 125

Text #16

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.1035. Min Act: -0.1700

Data Index: 1102719 (Open Web Text)

Max Activating Token Index: 933

Text #17

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.1378. Min Act: -0.1700

Data Index: 4914596 (Open Web Text)

Max Activating Token Index: 959

Text #18

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.1361. Min Act: -0.1700

Data Index: 6495381 (Open Web Text)

Max Activating Token Index: 260

Text #19

Max Range: 3.5866. Min Range: -3.5866

Max Act: 3.1109. Min Act: -0.1700

Data Index: 6756590 (Open Web Text)

Max Activating Token Index: 914