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

Dataset: Open Web Text

Neuron 829 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: 3.3348. Min Range: -3.3348

Max Act: 3.3348. Min Act: -0.1700

Data Index: 1695691 (Open Web Text)

Max Activating Token Index: 771

Text #1

Max Range: 3.3348. Min Range: -3.3348

Max Act: 3.1845. Min Act: -0.1700

Data Index: 7510381 (Open Web Text)

Max Activating Token Index: 139

Text #2

Max Range: 3.3348. Min Range: -3.3348

Max Act: 3.0824. Min Act: -0.1700

Data Index: 6963162 (Open Web Text)

Max Activating Token Index: 586

Text #3

Max Range: 3.3348. Min Range: -3.3348

Max Act: 2.9817. Min Act: -0.1700

Data Index: 3510962 (Open Web Text)

Max Activating Token Index: 361

Text #4

Max Range: 3.3348. Min Range: -3.3348

Max Act: 2.9838. Min Act: -0.1700

Data Index: 6534794 (Open Web Text)

Max Activating Token Index: 29

Text #5

Max Range: 3.3348. Min Range: -3.3348

Max Act: 2.9371. Min Act: -0.1700

Data Index: 8116052 (Open Web Text)

Max Activating Token Index: 505

Text #6

Max Range: 3.3348. Min Range: -3.3348

Max Act: 2.9238. Min Act: -0.1700

Data Index: 6332993 (Open Web Text)

Max Activating Token Index: 597

Text #7

Max Range: 3.3348. Min Range: -3.3348

Max Act: 2.8962. Min Act: -0.1700

Data Index: 7209808 (Open Web Text)

Max Activating Token Index: 635

Text #8

Max Range: 3.3348. Min Range: -3.3348

Max Act: 2.9025. Min Act: -0.1700

Data Index: 3212149 (Open Web Text)

Max Activating Token Index: 659

Text #9

Max Range: 3.3348. Min Range: -3.3348

Max Act: 2.8852. Min Act: -0.1700

Data Index: 71892 (Open Web Text)

Max Activating Token Index: 988

Text #10

Max Range: 3.3348. Min Range: -3.3348

Max Act: 2.8680. Min Act: -0.1700

Data Index: 1030526 (Open Web Text)

Max Activating Token Index: 470

Text #11

Max Range: 3.3348. Min Range: -3.3348

Max Act: 2.9080. Min Act: -0.1700

Data Index: 5378358 (Open Web Text)

Max Activating Token Index: 94

Text #12

Max Range: 3.3348. Min Range: -3.3348

Max Act: 2.8646. Min Act: -0.1700

Data Index: 5233758 (Open Web Text)

Max Activating Token Index: 60

Text #13

Max Range: 3.3348. Min Range: -3.3348

Max Act: 2.8903. Min Act: -0.1700

Data Index: 6993745 (Open Web Text)

Max Activating Token Index: 210

Text #14

Max Range: 3.3348. Min Range: -3.3348

Max Act: 2.8788. Min Act: -0.1700

Data Index: 2146032 (Open Web Text)

Max Activating Token Index: 211

Text #15

Max Range: 3.3348. Min Range: -3.3348

Max Act: 2.8809. Min Act: -0.1700

Data Index: 7548888 (Open Web Text)

Max Activating Token Index: 532

Text #16

Max Range: 3.3348. Min Range: -3.3348

Max Act: 2.8533. Min Act: -0.1700

Data Index: 676430 (Open Web Text)

Max Activating Token Index: 550

Text #17

Max Range: 3.3348. Min Range: -3.3348

Max Act: 2.8921. Min Act: -0.1700

Data Index: 7733608 (Open Web Text)

Max Activating Token Index: 315

Text #18

Max Range: 3.3348. Min Range: -3.3348

Max Act: 2.8638. Min Act: -0.1700

Data Index: 6000491 (Open Web Text)

Max Activating Token Index: 652

Text #19

Max Range: 3.3348. Min Range: -3.3348

Max Act: 2.8527. Min Act: -0.1700

Data Index: 1224675 (Open Web Text)

Max Activating Token Index: 300