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

Dataset: Open Web Text

Neuron 109 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: 1.7858. Min Range: -1.7858

Max Act: 1.7858. Min Act: -0.1641

Data Index: 3825641 (Open Web Text)

Max Activating Token Index: 735

Text #1

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.7717. Min Act: -0.1699

Data Index: 6486486 (Open Web Text)

Max Activating Token Index: 592

Text #2

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.7464. Min Act: -0.1700

Data Index: 5252328 (Open Web Text)

Max Activating Token Index: 71

Text #3

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.7478. Min Act: -0.1655

Data Index: 3373550 (Open Web Text)

Max Activating Token Index: 342

Text #4

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.7273. Min Act: -0.1700

Data Index: 3256500 (Open Web Text)

Max Activating Token Index: 476

Text #5

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.7316. Min Act: -0.1682

Data Index: 6334148 (Open Web Text)

Max Activating Token Index: 921

Text #6

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.7343. Min Act: -0.1700

Data Index: 2349618 (Open Web Text)

Max Activating Token Index: 233

Text #7

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.7347. Min Act: -0.1700

Data Index: 2722478 (Open Web Text)

Max Activating Token Index: 549

Text #8

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.7227. Min Act: -0.1700

Data Index: 8721783 (Open Web Text)

Max Activating Token Index: 208

Text #9

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.7094. Min Act: -0.1694

Data Index: 6055443 (Open Web Text)

Max Activating Token Index: 711

Text #10

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.7093. Min Act: -0.1700

Data Index: 6932223 (Open Web Text)

Max Activating Token Index: 818

Text #11

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.7038. Min Act: -0.1700

Data Index: 1713791 (Open Web Text)

Max Activating Token Index: 397

Text #12

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.7031. Min Act: -0.1700

Data Index: 4037389 (Open Web Text)

Max Activating Token Index: 595

Text #13

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.7005. Min Act: -0.1700

Data Index: 1711023 (Open Web Text)

Max Activating Token Index: 31

Text #14

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.6955. Min Act: -0.1700

Data Index: 4656846 (Open Web Text)

Max Activating Token Index: 643

Text #15

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.6989. Min Act: -0.1694

Data Index: 2319566 (Open Web Text)

Max Activating Token Index: 46

Text #16

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.7013. Min Act: -0.1698

Data Index: 5601123 (Open Web Text)

Max Activating Token Index: 21

Text #17

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.6992. Min Act: -0.1698

Data Index: 1950050 (Open Web Text)

Max Activating Token Index: 593

Text #18

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.6984. Min Act: -0.1700

Data Index: 6670059 (Open Web Text)

Max Activating Token Index: 42

Text #19

Max Range: 1.7858. Min Range: -1.7858

Max Act: 1.6799. Min Act: -0.1700

Data Index: 2323534 (Open Web Text)

Max Activating Token Index: 515