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

Dataset: Open Web Text

Neuron 2182 in Layer 3

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: 3.8478. Min Range: -3.8478

Max Act: 3.8478. Min Act: -0.1700

Data Index: 8040448 (Open Web Text)

Max Activating Token Index: 479

Text #1

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.7619. Min Act: -0.1700

Data Index: 8049788 (Open Web Text)

Max Activating Token Index: 429

Text #2

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.7440. Min Act: -0.1700

Data Index: 1922736 (Open Web Text)

Max Activating Token Index: 512

Text #3

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.6842. Min Act: -0.1700

Data Index: 1173091 (Open Web Text)

Max Activating Token Index: 97

Text #4

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.6421. Min Act: -0.1700

Data Index: 4138307 (Open Web Text)

Max Activating Token Index: 978

Text #5

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.5877. Min Act: -0.1700

Data Index: 1927602 (Open Web Text)

Max Activating Token Index: 960

Text #6

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.6286. Min Act: -0.1700

Data Index: 60557 (Open Web Text)

Max Activating Token Index: 969

Text #7

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.6370. Min Act: -0.1700

Data Index: 3927517 (Open Web Text)

Max Activating Token Index: 502

Text #8

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.6447. Min Act: -0.1700

Data Index: 6333882 (Open Web Text)

Max Activating Token Index: 787

Text #9

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.5623. Min Act: -0.1700

Data Index: 69198 (Open Web Text)

Max Activating Token Index: 410

Text #10

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.6122. Min Act: -0.1700

Data Index: 8002916 (Open Web Text)

Max Activating Token Index: 825

Text #11

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.5797. Min Act: -0.1700

Data Index: 7697257 (Open Web Text)

Max Activating Token Index: 100

Text #12

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.5721. Min Act: -0.1700

Data Index: 3844047 (Open Web Text)

Max Activating Token Index: 456

Text #13

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.5530. Min Act: -0.1700

Data Index: 1105777 (Open Web Text)

Max Activating Token Index: 464

Text #14

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.5620. Min Act: -0.1700

Data Index: 8575413 (Open Web Text)

Max Activating Token Index: 407

Text #15

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.5838. Min Act: -0.1700

Data Index: 3238791 (Open Web Text)

Max Activating Token Index: 281

Text #16

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.5668. Min Act: -0.1700

Data Index: 3508343 (Open Web Text)

Max Activating Token Index: 888

Text #17

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.5383. Min Act: -0.1700

Data Index: 7615582 (Open Web Text)

Max Activating Token Index: 552

Text #18

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.4940. Min Act: -0.1700

Data Index: 6361121 (Open Web Text)

Max Activating Token Index: 988

Text #19

Max Range: 3.8478. Min Range: -3.8478

Max Act: 3.5332. Min Act: -0.1700

Data Index: 6204791 (Open Web Text)

Max Activating Token Index: 849