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

Dataset: Open Web Text

Neuron 387 in Layer 5

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: 4.6239. Min Range: -4.6239

Max Act: 4.6079. Min Act: -0.1700

Data Index: 6195747 (Open Web Text)

Max Activating Token Index: 528

Text #1

Max Range: 4.6239. Min Range: -4.6239

Max Act: 4.5982. Min Act: -0.1700

Data Index: 4863583 (Open Web Text)

Max Activating Token Index: 612

Text #2

Max Range: 4.6239. Min Range: -4.6239

Max Act: 4.6239. Min Act: -0.1700

Data Index: 2409317 (Open Web Text)

Max Activating Token Index: 1007

Text #3

Max Range: 4.6239. Min Range: -4.6239

Max Act: 4.5774. Min Act: -0.1700

Data Index: 6195748 (Open Web Text)

Max Activating Token Index: 952

Text #4

Max Range: 4.6239. Min Range: -4.6239

Max Act: 4.5683. Min Act: -0.1700

Data Index: 3632452 (Open Web Text)

Max Activating Token Index: 772

Text #5

Max Range: 4.6239. Min Range: -4.6239

Max Act: 4.5552. Min Act: -0.1700

Data Index: 5086000 (Open Web Text)

Max Activating Token Index: 378

Text #6

Max Range: 4.6239. Min Range: -4.6239

Max Act: 4.5735. Min Act: -0.1700

Data Index: 5926535 (Open Web Text)

Max Activating Token Index: 731

Text #7

Max Range: 4.6239. Min Range: -4.6239

Max Act: 4.5751. Min Act: -0.1700

Data Index: 4221212 (Open Web Text)

Max Activating Token Index: 853

Text #8

Max Range: 4.6239. Min Range: -4.6239

Max Act: 4.5157. Min Act: -0.1700

Data Index: 2409319 (Open Web Text)

Max Activating Token Index: 408

Text #9

Max Range: 4.6239. Min Range: -4.6239

Max Act: 4.5213. Min Act: -0.1700

Data Index: 3539455 (Open Web Text)

Max Activating Token Index: 492

Text #10

Max Range: 4.6239. Min Range: -4.6239

Max Act: 4.5313. Min Act: -0.1700

Data Index: 5926537 (Open Web Text)

Max Activating Token Index: 132

Text #11

Max Range: 4.6239. Min Range: -4.6239

Max Act: 4.5376. Min Act: -0.1700

Data Index: 5504012 (Open Web Text)

Max Activating Token Index: 139

Text #12

Max Range: 4.6239. Min Range: -4.6239

Max Act: 4.5060. Min Act: -0.1700

Data Index: 3359874 (Open Web Text)

Max Activating Token Index: 620

Text #13

Max Range: 4.6239. Min Range: -4.6239

Max Act: 4.5294. Min Act: -0.1700

Data Index: 4152150 (Open Web Text)

Max Activating Token Index: 604

Text #14

Max Range: 4.6239. Min Range: -4.6239

Max Act: 4.5373. Min Act: -0.1700

Data Index: 1350399 (Open Web Text)

Max Activating Token Index: 149

Text #15

Max Range: 4.6239. Min Range: -4.6239

Max Act: 4.5436. Min Act: -0.1700

Data Index: 4109507 (Open Web Text)

Max Activating Token Index: 993

Text #16

Max Range: 4.6239. Min Range: -4.6239

Max Act: 4.4992. Min Act: -0.1700

Data Index: 5348770 (Open Web Text)

Max Activating Token Index: 305

Text #17

Max Range: 4.6239. Min Range: -4.6239

Max Act: 4.5193. Min Act: -0.1700

Data Index: 4760331 (Open Web Text)

Max Activating Token Index: 377

Text #18

Max Range: 4.6239. Min Range: -4.6239

Max Act: 4.4899. Min Act: -0.1700

Data Index: 3106918 (Open Web Text)

Max Activating Token Index: 977

Text #19

Max Range: 4.6239. Min Range: -4.6239

Max Act: 4.5234. Min Act: -0.1700

Data Index: 6021745 (Open Web Text)

Max Activating Token Index: 749