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

Dataset: Open Web Text

Neuron 1607 in Layer 4

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: 3.1456. Min Range: -3.1456

Max Act: 3.1456. Min Act: -0.1700

Data Index: 953980 (Open Web Text)

Max Activating Token Index: 1012

Text #1

Max Range: 3.1456. Min Range: -3.1456

Max Act: 3.1040. Min Act: -0.1700

Data Index: 8673417 (Open Web Text)

Max Activating Token Index: 664

Text #2

Max Range: 3.1456. Min Range: -3.1456

Max Act: 3.0931. Min Act: -0.1700

Data Index: 8292666 (Open Web Text)

Max Activating Token Index: 370

Text #3

Max Range: 3.1456. Min Range: -3.1456

Max Act: 3.0846. Min Act: -0.1700

Data Index: 2287393 (Open Web Text)

Max Activating Token Index: 354

Text #4

Max Range: 3.1456. Min Range: -3.1456

Max Act: 3.0645. Min Act: -0.1700

Data Index: 5311869 (Open Web Text)

Max Activating Token Index: 595

Text #5

Max Range: 3.1456. Min Range: -3.1456

Max Act: 3.0797. Min Act: -0.1700

Data Index: 8559404 (Open Web Text)

Max Activating Token Index: 336

Text #6

Max Range: 3.1456. Min Range: -3.1456

Max Act: 3.0710. Min Act: -0.1700

Data Index: 2139666 (Open Web Text)

Max Activating Token Index: 479

Text #7

Max Range: 3.1456. Min Range: -3.1456

Max Act: 3.0460. Min Act: -0.1700

Data Index: 3160040 (Open Web Text)

Max Activating Token Index: 298

Text #8

Max Range: 3.1456. Min Range: -3.1456

Max Act: 3.0312. Min Act: -0.1700

Data Index: 5416955 (Open Web Text)

Max Activating Token Index: 461

Text #9

Max Range: 3.1456. Min Range: -3.1456

Max Act: 3.0274. Min Act: -0.1700

Data Index: 5143757 (Open Web Text)

Max Activating Token Index: 544

Text #10

Max Range: 3.1456. Min Range: -3.1456

Max Act: 3.0077. Min Act: -0.1700

Data Index: 7823943 (Open Web Text)

Max Activating Token Index: 165

Text #11

Max Range: 3.1456. Min Range: -3.1456

Max Act: 3.0135. Min Act: -0.1700

Data Index: 745550 (Open Web Text)

Max Activating Token Index: 999

Text #12

Max Range: 3.1456. Min Range: -3.1456

Max Act: 2.9864. Min Act: -0.1700

Data Index: 4590864 (Open Web Text)

Max Activating Token Index: 661

Text #13

Max Range: 3.1456. Min Range: -3.1456

Max Act: 3.0112. Min Act: -0.1700

Data Index: 8385603 (Open Web Text)

Max Activating Token Index: 410

Text #14

Max Range: 3.1456. Min Range: -3.1456

Max Act: 3.0098. Min Act: -0.1700

Data Index: 4415734 (Open Web Text)

Max Activating Token Index: 991

Text #15

Max Range: 3.1456. Min Range: -3.1456

Max Act: 2.9735. Min Act: -0.1700

Data Index: 478196 (Open Web Text)

Max Activating Token Index: 578

Text #16

Max Range: 3.1456. Min Range: -3.1456

Max Act: 3.0004. Min Act: -0.1700

Data Index: 3455727 (Open Web Text)

Max Activating Token Index: 171

Text #17

Max Range: 3.1456. Min Range: -3.1456

Max Act: 3.0076. Min Act: -0.1700

Data Index: 8507223 (Open Web Text)

Max Activating Token Index: 531

Text #18

Max Range: 3.1456. Min Range: -3.1456

Max Act: 2.9757. Min Act: -0.1700

Data Index: 5375848 (Open Web Text)

Max Activating Token Index: 178

Text #19

Max Range: 3.1456. Min Range: -3.1456

Max Act: 2.9878. Min Act: -0.1700

Data Index: 1396726 (Open Web Text)

Max Activating Token Index: 263