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

Dataset: Open Web Text

Neuron 304 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: 2.0625. Min Range: -2.0625

Max Act: 2.0625. Min Act: -0.1700

Data Index: 6258499 (Open Web Text)

Max Activating Token Index: 503

Text #1

Max Range: 2.0625. Min Range: -2.0625

Max Act: 2.0517. Min Act: -0.1700

Data Index: 6258505 (Open Web Text)

Max Activating Token Index: 203

Text #2

Max Range: 2.0625. Min Range: -2.0625

Max Act: 2.0166. Min Act: -0.1700

Data Index: 6258496 (Open Web Text)

Max Activating Token Index: 788

Text #3

Max Range: 2.0625. Min Range: -2.0625

Max Act: 2.0246. Min Act: -0.1700

Data Index: 3068102 (Open Web Text)

Max Activating Token Index: 829

Text #4

Max Range: 2.0625. Min Range: -2.0625

Max Act: 1.9973. Min Act: -0.1698

Data Index: 6258504 (Open Web Text)

Max Activating Token Index: 356

Text #5

Max Range: 2.0625. Min Range: -2.0625

Max Act: 1.9772. Min Act: -0.1700

Data Index: 757101 (Open Web Text)

Max Activating Token Index: 89

Text #6

Max Range: 2.0625. Min Range: -2.0625

Max Act: 1.9731. Min Act: -0.1700

Data Index: 3229349 (Open Web Text)

Max Activating Token Index: 149

Text #7

Max Range: 2.0625. Min Range: -2.0625

Max Act: 1.9499. Min Act: -0.1699

Data Index: 6258500 (Open Web Text)

Max Activating Token Index: 24

Text #8

Max Range: 2.0625. Min Range: -2.0625

Max Act: 1.9411. Min Act: -0.1700

Data Index: 6258503 (Open Web Text)

Max Activating Token Index: 115

Text #9

Max Range: 2.0625. Min Range: -2.0625

Max Act: 1.9512. Min Act: -0.1700

Data Index: 5992969 (Open Web Text)

Max Activating Token Index: 373

Text #10

Max Range: 2.0625. Min Range: -2.0625

Max Act: 1.9545. Min Act: -0.1700

Data Index: 6258493 (Open Web Text)

Max Activating Token Index: 364

Text #11

Max Range: 2.0625. Min Range: -2.0625

Max Act: 1.9205. Min Act: -0.1700

Data Index: 6258502 (Open Web Text)

Max Activating Token Index: 358

Text #12

Max Range: 2.0625. Min Range: -2.0625

Max Act: 1.9339. Min Act: -0.1700

Data Index: 8509057 (Open Web Text)

Max Activating Token Index: 330

Text #13

Max Range: 2.0625. Min Range: -2.0625

Max Act: 1.9146. Min Act: -0.1700

Data Index: 4615615 (Open Web Text)

Max Activating Token Index: 683

Text #14

Max Range: 2.0625. Min Range: -2.0625

Max Act: 1.8830. Min Act: -0.1700

Data Index: 8509055 (Open Web Text)

Max Activating Token Index: 917

Text #15

Max Range: 2.0625. Min Range: -2.0625

Max Act: 1.8735. Min Act: -0.1700

Data Index: 6258495 (Open Web Text)

Max Activating Token Index: 271

Text #16

Max Range: 2.0625. Min Range: -2.0625

Max Act: 1.8747. Min Act: -0.1700

Data Index: 6913234 (Open Web Text)

Max Activating Token Index: 874

Text #17

Max Range: 2.0625. Min Range: -2.0625

Max Act: 1.8776. Min Act: -0.1689

Data Index: 4945201 (Open Web Text)

Max Activating Token Index: 196

Text #18

Max Range: 2.0625. Min Range: -2.0625

Max Act: 1.8643. Min Act: -0.1700

Data Index: 8250950 (Open Web Text)

Max Activating Token Index: 853

Text #19

Max Range: 2.0625. Min Range: -2.0625

Max Act: 1.8691. Min Act: -0.1700

Data Index: 6258498 (Open Web Text)

Max Activating Token Index: 541