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

Dataset: Open Web Text

Neuron 46 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: 1.9723. Min Range: -1.9723

Max Act: 1.9619. Min Act: -0.1700

Data Index: 4392894 (Open Web Text)

Max Activating Token Index: 412

Text #1

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.9723. Min Act: -0.1700

Data Index: 8435728 (Open Web Text)

Max Activating Token Index: 23

Text #2

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.9231. Min Act: -0.1700

Data Index: 1342709 (Open Web Text)

Max Activating Token Index: 67

Text #3

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.9275. Min Act: -0.1700

Data Index: 671168 (Open Web Text)

Max Activating Token Index: 384

Text #4

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.9201. Min Act: -0.1700

Data Index: 6547558 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.9379. Min Act: -0.1700

Data Index: 546590 (Open Web Text)

Max Activating Token Index: 188

Text #6

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.9279. Min Act: -0.1693

Data Index: 3118223 (Open Web Text)

Max Activating Token Index: 398

Text #7

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.9088. Min Act: -0.1700

Data Index: 5101283 (Open Web Text)

Max Activating Token Index: 279

Text #8

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.9231. Min Act: -0.1700

Data Index: 5336617 (Open Web Text)

Max Activating Token Index: 475

Text #9

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.9094. Min Act: -0.1700

Data Index: 4272536 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.9041. Min Act: -0.1700

Data Index: 1069633 (Open Web Text)

Max Activating Token Index: 605

Text #11

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.9079. Min Act: -0.1700

Data Index: 4590184 (Open Web Text)

Max Activating Token Index: 434

Text #12

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.9166. Min Act: -0.1700

Data Index: 5336618 (Open Web Text)

Max Activating Token Index: 466

Text #13

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.8935. Min Act: -0.1700

Data Index: 173812 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.8978. Min Act: -0.1694

Data Index: 4964707 (Open Web Text)

Max Activating Token Index: 474

Text #15

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.9050. Min Act: -0.1700

Data Index: 7508745 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.8932. Min Act: -0.1700

Data Index: 5399944 (Open Web Text)

Max Activating Token Index: 57

Text #17

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.8802. Min Act: -0.1700

Data Index: 518372 (Open Web Text)

Max Activating Token Index: 713

Text #18

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.8798. Min Act: -0.1700

Data Index: 3277639 (Open Web Text)

Max Activating Token Index: 576

Text #19

Max Range: 1.9723. Min Range: -1.9723

Max Act: 1.8750. Min Act: -0.1700

Data Index: 2512852 (Open Web Text)

Max Activating Token Index: 351