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

Dataset: Open Web Text

Neuron 1663 in Layer 6

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: 4.8971. Min Range: -4.8971

Max Act: 4.8971. Min Act: -0.1700

Data Index: 5802688 (Open Web Text)

Max Activating Token Index: 804

Text #1

Max Range: 4.8971. Min Range: -4.8971

Max Act: 4.8504. Min Act: -0.1700

Data Index: 2465056 (Open Web Text)

Max Activating Token Index: 1003

Text #2

Max Range: 4.8971. Min Range: -4.8971

Max Act: 4.6503. Min Act: -0.1700

Data Index: 2704943 (Open Web Text)

Max Activating Token Index: 974

Text #3

Max Range: 4.8971. Min Range: -4.8971

Max Act: 4.6156. Min Act: -0.1700

Data Index: 1232649 (Open Web Text)

Max Activating Token Index: 843

Text #4

Max Range: 4.8971. Min Range: -4.8971

Max Act: 4.5758. Min Act: -0.1700

Data Index: 5538421 (Open Web Text)

Max Activating Token Index: 925

Text #5

Max Range: 4.8971. Min Range: -4.8971

Max Act: 4.5848. Min Act: -0.1700

Data Index: 4753183 (Open Web Text)

Max Activating Token Index: 939

Text #6

Max Range: 4.8971. Min Range: -4.8971

Max Act: 4.5633. Min Act: -0.1700

Data Index: 1536890 (Open Web Text)

Max Activating Token Index: 453

Text #7

Max Range: 4.8971. Min Range: -4.8971

Max Act: 4.5358. Min Act: -0.1700

Data Index: 2585764 (Open Web Text)

Max Activating Token Index: 856

Text #8

Max Range: 4.8971. Min Range: -4.8971

Max Act: 4.5266. Min Act: -0.1700

Data Index: 3193413 (Open Web Text)

Max Activating Token Index: 952

Text #9

Max Range: 4.8971. Min Range: -4.8971

Max Act: 4.4893. Min Act: -0.1700

Data Index: 4397091 (Open Web Text)

Max Activating Token Index: 570

Text #10

Max Range: 4.8971. Min Range: -4.8971

Max Act: 4.4396. Min Act: -0.1700

Data Index: 2959111 (Open Web Text)

Max Activating Token Index: 886

Text #11

Max Range: 4.8971. Min Range: -4.8971

Max Act: 4.4608. Min Act: -0.1700

Data Index: 7598970 (Open Web Text)

Max Activating Token Index: 853

Text #12

Max Range: 4.8971. Min Range: -4.8971

Max Act: 4.4296. Min Act: -0.1700

Data Index: 7478728 (Open Web Text)

Max Activating Token Index: 744

Text #13

Max Range: 4.8971. Min Range: -4.8971

Max Act: 4.4455. Min Act: -0.1700

Data Index: 2115381 (Open Web Text)

Max Activating Token Index: 634

Text #14

Max Range: 4.8971. Min Range: -4.8971

Max Act: 4.4510. Min Act: -0.1700

Data Index: 6969076 (Open Web Text)

Max Activating Token Index: 741

Text #15

Max Range: 4.8971. Min Range: -4.8971

Max Act: 4.4243. Min Act: -0.1700

Data Index: 4319118 (Open Web Text)

Max Activating Token Index: 804

Text #16

Max Range: 4.8971. Min Range: -4.8971

Max Act: 4.4087. Min Act: -0.1700

Data Index: 1747131 (Open Web Text)

Max Activating Token Index: 1017

Text #17

Max Range: 4.8971. Min Range: -4.8971

Max Act: 4.4154. Min Act: -0.1700

Data Index: 6969363 (Open Web Text)

Max Activating Token Index: 575

Text #18

Max Range: 4.8971. Min Range: -4.8971

Max Act: 4.4337. Min Act: -0.1700

Data Index: 7645282 (Open Web Text)

Max Activating Token Index: 618

Text #19

Max Range: 4.8971. Min Range: -4.8971

Max Act: 4.4408. Min Act: -0.1700

Data Index: 184180 (Open Web Text)

Max Activating Token Index: 650