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

Dataset: Open Web Text

Neuron 150 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: 3.5731. Min Range: -3.5731

Max Act: 3.5665. Min Act: -0.1700

Data Index: 7013211 (Open Web Text)

Max Activating Token Index: 462

Text #1

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.5358. Min Act: -0.1700

Data Index: 747839 (Open Web Text)

Max Activating Token Index: 397

Text #2

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.5731. Min Act: -0.1700

Data Index: 6408712 (Open Web Text)

Max Activating Token Index: 182

Text #3

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.5213. Min Act: -0.1700

Data Index: 2221823 (Open Web Text)

Max Activating Token Index: 386

Text #4

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.5342. Min Act: -0.1700

Data Index: 3737565 (Open Web Text)

Max Activating Token Index: 725

Text #5

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.5200. Min Act: -0.1700

Data Index: 6846347 (Open Web Text)

Max Activating Token Index: 885

Text #6

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.5063. Min Act: -0.1700

Data Index: 5143876 (Open Web Text)

Max Activating Token Index: 288

Text #7

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.4869. Min Act: -0.1700

Data Index: 2611831 (Open Web Text)

Max Activating Token Index: 407

Text #8

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.4789. Min Act: -0.1700

Data Index: 164176 (Open Web Text)

Max Activating Token Index: 430

Text #9

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.5054. Min Act: -0.1700

Data Index: 3406847 (Open Web Text)

Max Activating Token Index: 914

Text #10

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.5066. Min Act: -0.1700

Data Index: 3879635 (Open Web Text)

Max Activating Token Index: 442

Text #11

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.4782. Min Act: -0.1700

Data Index: 3132998 (Open Web Text)

Max Activating Token Index: 469

Text #12

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.4567. Min Act: -0.1700

Data Index: 5854809 (Open Web Text)

Max Activating Token Index: 301

Text #13

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.4405. Min Act: -0.1700

Data Index: 483162 (Open Web Text)

Max Activating Token Index: 714

Text #14

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.4478. Min Act: -0.1700

Data Index: 1004922 (Open Web Text)

Max Activating Token Index: 921

Text #15

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.4495. Min Act: -0.1700

Data Index: 2539897 (Open Web Text)

Max Activating Token Index: 279

Text #16

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.4604. Min Act: -0.1700

Data Index: 5460715 (Open Web Text)

Max Activating Token Index: 430

Text #17

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.4026. Min Act: -0.1700

Data Index: 5406 (Open Web Text)

Max Activating Token Index: 513

Text #18

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.4308. Min Act: -0.1700

Data Index: 2731189 (Open Web Text)

Max Activating Token Index: 316

Text #19

Max Range: 3.5731. Min Range: -3.5731

Max Act: 3.4324. Min Act: -0.1700

Data Index: 5950102 (Open Web Text)

Max Activating Token Index: 720