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

Dataset: Open Web Text

Neuron 384 in Layer 6

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: 4.7196. Min Range: -4.7196

Max Act: 4.7196. Min Act: -0.1700

Data Index: 8642484 (Open Web Text)

Max Activating Token Index: 480

Text #1

Max Range: 4.7196. Min Range: -4.7196

Max Act: 4.3401. Min Act: -0.1700

Data Index: 2198420 (Open Web Text)

Max Activating Token Index: 996

Text #2

Max Range: 4.7196. Min Range: -4.7196

Max Act: 4.2070. Min Act: -0.1700

Data Index: 5640699 (Open Web Text)

Max Activating Token Index: 335

Text #3

Max Range: 4.7196. Min Range: -4.7196

Max Act: 4.1629. Min Act: -0.1700

Data Index: 5614814 (Open Web Text)

Max Activating Token Index: 597

Text #4

Max Range: 4.7196. Min Range: -4.7196

Max Act: 4.0623. Min Act: -0.1700

Data Index: 2088775 (Open Web Text)

Max Activating Token Index: 916

Text #5

Max Range: 4.7196. Min Range: -4.7196

Max Act: 4.0462. Min Act: -0.1700

Data Index: 392743 (Open Web Text)

Max Activating Token Index: 941

Text #6

Max Range: 4.7196. Min Range: -4.7196

Max Act: 4.0371. Min Act: -0.1700

Data Index: 4853917 (Open Web Text)

Max Activating Token Index: 579

Text #7

Max Range: 4.7196. Min Range: -4.7196

Max Act: 4.0658. Min Act: -0.1700

Data Index: 1469517 (Open Web Text)

Max Activating Token Index: 535

Text #8

Max Range: 4.7196. Min Range: -4.7196

Max Act: 3.9786. Min Act: -0.1700

Data Index: 4421683 (Open Web Text)

Max Activating Token Index: 415

Text #9

Max Range: 4.7196. Min Range: -4.7196

Max Act: 4.0019. Min Act: -0.1700

Data Index: 7238479 (Open Web Text)

Max Activating Token Index: 273

Text #10

Max Range: 4.7196. Min Range: -4.7196

Max Act: 3.9887. Min Act: -0.1700

Data Index: 8102083 (Open Web Text)

Max Activating Token Index: 474

Text #11

Max Range: 4.7196. Min Range: -4.7196

Max Act: 4.0106. Min Act: -0.1700

Data Index: 7373232 (Open Web Text)

Max Activating Token Index: 776

Text #12

Max Range: 4.7196. Min Range: -4.7196

Max Act: 3.9728. Min Act: -0.1700

Data Index: 661194 (Open Web Text)

Max Activating Token Index: 229

Text #13

Max Range: 4.7196. Min Range: -4.7196

Max Act: 3.9958. Min Act: -0.1699

Data Index: 2179613 (Open Web Text)

Max Activating Token Index: 468

Text #14

Max Range: 4.7196. Min Range: -4.7196

Max Act: 3.9793. Min Act: -0.1700

Data Index: 5002875 (Open Web Text)

Max Activating Token Index: 94

Text #15

Max Range: 4.7196. Min Range: -4.7196

Max Act: 3.9642. Min Act: -0.1700

Data Index: 3488127 (Open Web Text)

Max Activating Token Index: 61

Text #16

Max Range: 4.7196. Min Range: -4.7196

Max Act: 3.9418. Min Act: -0.1700

Data Index: 3379463 (Open Web Text)

Max Activating Token Index: 837

Text #17

Max Range: 4.7196. Min Range: -4.7196

Max Act: 3.9703. Min Act: -0.1700

Data Index: 4853151 (Open Web Text)

Max Activating Token Index: 256

Text #18

Max Range: 4.7196. Min Range: -4.7196

Max Act: 3.9681. Min Act: -0.1700

Data Index: 1722823 (Open Web Text)

Max Activating Token Index: 231

Text #19

Max Range: 4.7196. Min Range: -4.7196

Max Act: 3.9538. Min Act: -0.1700

Data Index: 7675005 (Open Web Text)

Max Activating Token Index: 256