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

Dataset: Open Web Text

Neuron 1537 in Layer 2

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: 3.3975. Min Range: -3.3975

Max Act: 3.3975. Min Act: -0.1700

Data Index: 8394795 (Open Web Text)

Max Activating Token Index: 156

Text #1

Max Range: 3.3975. Min Range: -3.3975

Max Act: 3.3919. Min Act: -0.1700

Data Index: 1113621 (Open Web Text)

Max Activating Token Index: 18

Text #2

Max Range: 3.3975. Min Range: -3.3975

Max Act: 3.3455. Min Act: -0.1700

Data Index: 5982712 (Open Web Text)

Max Activating Token Index: 949

Text #3

Max Range: 3.3975. Min Range: -3.3975

Max Act: 3.3313. Min Act: -0.1700

Data Index: 4910779 (Open Web Text)

Max Activating Token Index: 12

Text #4

Max Range: 3.3975. Min Range: -3.3975

Max Act: 3.2760. Min Act: -0.1700

Data Index: 7008593 (Open Web Text)

Max Activating Token Index: 528

Text #5

Max Range: 3.3975. Min Range: -3.3975

Max Act: 3.2399. Min Act: -0.1700

Data Index: 2543936 (Open Web Text)

Max Activating Token Index: 838

Text #6

Max Range: 3.3975. Min Range: -3.3975

Max Act: 3.2598. Min Act: -0.1700

Data Index: 1062771 (Open Web Text)

Max Activating Token Index: 215

Text #7

Max Range: 3.3975. Min Range: -3.3975

Max Act: 3.2412. Min Act: -0.1700

Data Index: 4593301 (Open Web Text)

Max Activating Token Index: 333

Text #8

Max Range: 3.3975. Min Range: -3.3975

Max Act: 3.2354. Min Act: -0.1700

Data Index: 5139190 (Open Web Text)

Max Activating Token Index: 118

Text #9

Max Range: 3.3975. Min Range: -3.3975

Max Act: 3.2230. Min Act: -0.1700

Data Index: 1228933 (Open Web Text)

Max Activating Token Index: 439

Text #10

Max Range: 3.3975. Min Range: -3.3975

Max Act: 3.2231. Min Act: -0.1700

Data Index: 5448290 (Open Web Text)

Max Activating Token Index: 31

Text #11

Max Range: 3.3975. Min Range: -3.3975

Max Act: 3.2007. Min Act: -0.1700

Data Index: 2063615 (Open Web Text)

Max Activating Token Index: 452

Text #12

Max Range: 3.3975. Min Range: -3.3975

Max Act: 3.1863. Min Act: -0.1700

Data Index: 1036158 (Open Web Text)

Max Activating Token Index: 322

Text #13

Max Range: 3.3975. Min Range: -3.3975

Max Act: 3.1967. Min Act: -0.1700

Data Index: 7178427 (Open Web Text)

Max Activating Token Index: 244

Text #14

Max Range: 3.3975. Min Range: -3.3975

Max Act: 3.2031. Min Act: -0.1700

Data Index: 5560827 (Open Web Text)

Max Activating Token Index: 496

Text #15

Max Range: 3.3975. Min Range: -3.3975

Max Act: 3.1847. Min Act: -0.1700

Data Index: 7488059 (Open Web Text)

Max Activating Token Index: 644

Text #16

Max Range: 3.3975. Min Range: -3.3975

Max Act: 3.1693. Min Act: -0.1700

Data Index: 4525284 (Open Web Text)

Max Activating Token Index: 140

Text #17

Max Range: 3.3975. Min Range: -3.3975

Max Act: 3.1709. Min Act: -0.1700

Data Index: 2671346 (Open Web Text)

Max Activating Token Index: 123

Text #18

Max Range: 3.3975. Min Range: -3.3975

Max Act: 3.1688. Min Act: -0.1700

Data Index: 2005424 (Open Web Text)

Max Activating Token Index: 445

Text #19

Max Range: 3.3975. Min Range: -3.3975

Max Act: 3.1550. Min Act: -0.1700

Data Index: 5231867 (Open Web Text)

Max Activating Token Index: 41