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

Dataset: Open Web Text

Neuron 1588 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: 1.5475. Min Range: -1.5475

Max Act: 1.5475. Min Act: -0.1700

Data Index: 3829853 (Open Web Text)

Max Activating Token Index: 62

Text #1

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.4890. Min Act: -0.1697

Data Index: 2654892 (Open Web Text)

Max Activating Token Index: 164

Text #2

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.4915. Min Act: -0.1652

Data Index: 1981162 (Open Web Text)

Max Activating Token Index: 77

Text #3

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.4785. Min Act: -0.1700

Data Index: 7786618 (Open Web Text)

Max Activating Token Index: 58

Text #4

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.4768. Min Act: -0.1660

Data Index: 373206 (Open Web Text)

Max Activating Token Index: 104

Text #5

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.4780. Min Act: -0.1700

Data Index: 6138255 (Open Web Text)

Max Activating Token Index: 133

Text #6

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.4830. Min Act: -0.1699

Data Index: 1693328 (Open Web Text)

Max Activating Token Index: 121

Text #7

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.4635. Min Act: -0.1697

Data Index: 4694254 (Open Web Text)

Max Activating Token Index: 572

Text #8

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.4728. Min Act: -0.1697

Data Index: 8518681 (Open Web Text)

Max Activating Token Index: 29

Text #9

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.4630. Min Act: -0.1700

Data Index: 2783918 (Open Web Text)

Max Activating Token Index: 205

Text #10

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.4694. Min Act: -0.1700

Data Index: 1650630 (Open Web Text)

Max Activating Token Index: 269

Text #11

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.4473. Min Act: -0.1699

Data Index: 6059264 (Open Web Text)

Max Activating Token Index: 172

Text #12

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.4391. Min Act: -0.1700

Data Index: 8536744 (Open Web Text)

Max Activating Token Index: 132

Text #13

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.4418. Min Act: -0.1698

Data Index: 5977093 (Open Web Text)

Max Activating Token Index: 71

Text #14

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.4405. Min Act: -0.1697

Data Index: 222434 (Open Web Text)

Max Activating Token Index: 538

Text #15

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.4375. Min Act: -0.1698

Data Index: 1140500 (Open Web Text)

Max Activating Token Index: 113

Text #16

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.4352. Min Act: -0.1700

Data Index: 8197941 (Open Web Text)

Max Activating Token Index: 850

Text #17

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.4335. Min Act: -0.1700

Data Index: 142424 (Open Web Text)

Max Activating Token Index: 700

Text #18

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.4305. Min Act: -0.1700

Data Index: 141997 (Open Web Text)

Max Activating Token Index: 812

Text #19

Max Range: 1.5475. Min Range: -1.5475

Max Act: 1.4266. Min Act: -0.1699

Data Index: 6169071 (Open Web Text)

Max Activating Token Index: 284