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

Dataset: Open Web Text

Neuron 81 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: 4.7525. Min Range: -4.7525

Max Act: 4.7525. Min Act: -0.1700

Data Index: 8558848 (Open Web Text)

Max Activating Token Index: 296

Text #1

Max Range: 4.7525. Min Range: -4.7525

Max Act: 4.7285. Min Act: -0.1700

Data Index: 1260975 (Open Web Text)

Max Activating Token Index: 920

Text #2

Max Range: 4.7525. Min Range: -4.7525

Max Act: 4.6136. Min Act: -0.1700

Data Index: 2193887 (Open Web Text)

Max Activating Token Index: 320

Text #3

Max Range: 4.7525. Min Range: -4.7525

Max Act: 4.5514. Min Act: -0.1700

Data Index: 1342832 (Open Web Text)

Max Activating Token Index: 669

Text #4

Max Range: 4.7525. Min Range: -4.7525

Max Act: 4.5127. Min Act: -0.1700

Data Index: 8465614 (Open Web Text)

Max Activating Token Index: 402

Text #5

Max Range: 4.7525. Min Range: -4.7525

Max Act: 4.4899. Min Act: -0.1700

Data Index: 2542203 (Open Web Text)

Max Activating Token Index: 791

Text #6

Max Range: 4.7525. Min Range: -4.7525

Max Act: 4.5057. Min Act: -0.1700

Data Index: 8617808 (Open Web Text)

Max Activating Token Index: 56

Text #7

Max Range: 4.7525. Min Range: -4.7525

Max Act: 4.5018. Min Act: -0.1700

Data Index: 8770558 (Open Web Text)

Max Activating Token Index: 833

Text #8

Max Range: 4.7525. Min Range: -4.7525

Max Act: 4.5057. Min Act: -0.1700

Data Index: 3764493 (Open Web Text)

Max Activating Token Index: 737

Text #9

Max Range: 4.7525. Min Range: -4.7525

Max Act: 4.4747. Min Act: -0.1700

Data Index: 4040817 (Open Web Text)

Max Activating Token Index: 409

Text #10

Max Range: 4.7525. Min Range: -4.7525

Max Act: 4.4817. Min Act: -0.1700

Data Index: 5602947 (Open Web Text)

Max Activating Token Index: 318

Text #11

Max Range: 4.7525. Min Range: -4.7525

Max Act: 4.4386. Min Act: -0.1700

Data Index: 1464140 (Open Web Text)

Max Activating Token Index: 585

Text #12

Max Range: 4.7525. Min Range: -4.7525

Max Act: 4.4004. Min Act: -0.1700

Data Index: 4803986 (Open Web Text)

Max Activating Token Index: 484

Text #13

Max Range: 4.7525. Min Range: -4.7525

Max Act: 4.4228. Min Act: -0.1700

Data Index: 6140232 (Open Web Text)

Max Activating Token Index: 126

Text #14

Max Range: 4.7525. Min Range: -4.7525

Max Act: 4.4222. Min Act: -0.1700

Data Index: 6329427 (Open Web Text)

Max Activating Token Index: 690

Text #15

Max Range: 4.7525. Min Range: -4.7525

Max Act: 4.4245. Min Act: -0.1700

Data Index: 5150146 (Open Web Text)

Max Activating Token Index: 487

Text #16

Max Range: 4.7525. Min Range: -4.7525

Max Act: 4.3954. Min Act: -0.1700

Data Index: 2345128 (Open Web Text)

Max Activating Token Index: 967

Text #17

Max Range: 4.7525. Min Range: -4.7525

Max Act: 4.3920. Min Act: -0.1700

Data Index: 5954750 (Open Web Text)

Max Activating Token Index: 244

Text #18

Max Range: 4.7525. Min Range: -4.7525

Max Act: 4.3773. Min Act: -0.1700

Data Index: 6303289 (Open Web Text)

Max Activating Token Index: 699

Text #19

Max Range: 4.7525. Min Range: -4.7525

Max Act: 4.3629. Min Act: -0.1700

Data Index: 4875459 (Open Web Text)

Max Activating Token Index: 667