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

Dataset: Open Web Text

Neuron 2008 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: 3.1512. Min Range: -3.1512

Max Act: 3.1411. Min Act: -0.1700

Data Index: 2546687 (Open Web Text)

Max Activating Token Index: 754

Text #1

Max Range: 3.1512. Min Range: -3.1512

Max Act: 3.1512. Min Act: -0.1700

Data Index: 6974384 (Open Web Text)

Max Activating Token Index: 431

Text #2

Max Range: 3.1512. Min Range: -3.1512

Max Act: 3.1246. Min Act: -0.1700

Data Index: 4685660 (Open Web Text)

Max Activating Token Index: 524

Text #3

Max Range: 3.1512. Min Range: -3.1512

Max Act: 3.1129. Min Act: -0.1700

Data Index: 8295122 (Open Web Text)

Max Activating Token Index: 384

Text #4

Max Range: 3.1512. Min Range: -3.1512

Max Act: 3.1416. Min Act: -0.1700

Data Index: 1808237 (Open Web Text)

Max Activating Token Index: 114

Text #5

Max Range: 3.1512. Min Range: -3.1512

Max Act: 3.1345. Min Act: -0.1700

Data Index: 6426932 (Open Web Text)

Max Activating Token Index: 313

Text #6

Max Range: 3.1512. Min Range: -3.1512

Max Act: 3.1179. Min Act: -0.1700

Data Index: 5538191 (Open Web Text)

Max Activating Token Index: 437

Text #7

Max Range: 3.1512. Min Range: -3.1512

Max Act: 3.1075. Min Act: -0.1700

Data Index: 7555746 (Open Web Text)

Max Activating Token Index: 943

Text #8

Max Range: 3.1512. Min Range: -3.1512

Max Act: 3.1140. Min Act: -0.1700

Data Index: 8270507 (Open Web Text)

Max Activating Token Index: 68

Text #9

Max Range: 3.1512. Min Range: -3.1512

Max Act: 3.0828. Min Act: -0.1700

Data Index: 6203365 (Open Web Text)

Max Activating Token Index: 318

Text #10

Max Range: 3.1512. Min Range: -3.1512

Max Act: 3.0922. Min Act: -0.1700

Data Index: 6764521 (Open Web Text)

Max Activating Token Index: 972

Text #11

Max Range: 3.1512. Min Range: -3.1512

Max Act: 3.0974. Min Act: -0.1700

Data Index: 5479789 (Open Web Text)

Max Activating Token Index: 661

Text #12

Max Range: 3.1512. Min Range: -3.1512

Max Act: 3.0967. Min Act: -0.1700

Data Index: 7607141 (Open Web Text)

Max Activating Token Index: 84

Text #13

Max Range: 3.1512. Min Range: -3.1512

Max Act: 3.0848. Min Act: -0.1700

Data Index: 434209 (Open Web Text)

Max Activating Token Index: 351

Text #14

Max Range: 3.1512. Min Range: -3.1512

Max Act: 3.0718. Min Act: -0.1700

Data Index: 920029 (Open Web Text)

Max Activating Token Index: 733

Text #15

Max Range: 3.1512. Min Range: -3.1512

Max Act: 3.0862. Min Act: -0.1700

Data Index: 8645408 (Open Web Text)

Max Activating Token Index: 264

Text #16

Max Range: 3.1512. Min Range: -3.1512

Max Act: 3.0587. Min Act: -0.1700

Data Index: 8274492 (Open Web Text)

Max Activating Token Index: 686

Text #17

Max Range: 3.1512. Min Range: -3.1512

Max Act: 3.0728. Min Act: -0.1700

Data Index: 3047748 (Open Web Text)

Max Activating Token Index: 738

Text #18

Max Range: 3.1512. Min Range: -3.1512

Max Act: 3.0644. Min Act: -0.1700

Data Index: 6267997 (Open Web Text)

Max Activating Token Index: 267

Text #19

Max Range: 3.1512. Min Range: -3.1512

Max Act: 3.0669. Min Act: -0.1700

Data Index: 3951377 (Open Web Text)

Max Activating Token Index: 487