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

Dataset: Open Web Text

Neuron 87 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: 5.3541. Min Range: -5.3541

Max Act: 5.3541. Min Act: -0.1700

Data Index: 767744 (Open Web Text)

Max Activating Token Index: 500

Text #1

Max Range: 5.3541. Min Range: -5.3541

Max Act: 5.1426. Min Act: -0.1700

Data Index: 767743 (Open Web Text)

Max Activating Token Index: 601

Text #2

Max Range: 5.3541. Min Range: -5.3541

Max Act: 5.0410. Min Act: -0.1700

Data Index: 5429060 (Open Web Text)

Max Activating Token Index: 703

Text #3

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.9129. Min Act: -0.1700

Data Index: 5201589 (Open Web Text)

Max Activating Token Index: 647

Text #4

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.9136. Min Act: -0.1700

Data Index: 8422448 (Open Web Text)

Max Activating Token Index: 339

Text #5

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.9004. Min Act: -0.1700

Data Index: 6545798 (Open Web Text)

Max Activating Token Index: 751

Text #6

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.8357. Min Act: -0.1700

Data Index: 3273351 (Open Web Text)

Max Activating Token Index: 210

Text #7

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.8272. Min Act: -0.1700

Data Index: 1523057 (Open Web Text)

Max Activating Token Index: 1007

Text #8

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.8176. Min Act: -0.1700

Data Index: 872258 (Open Web Text)

Max Activating Token Index: 777

Text #9

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.8208. Min Act: -0.1700

Data Index: 4836717 (Open Web Text)

Max Activating Token Index: 988

Text #10

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.7973. Min Act: -0.1700

Data Index: 6718284 (Open Web Text)

Max Activating Token Index: 831

Text #11

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.7582. Min Act: -0.1700

Data Index: 2890233 (Open Web Text)

Max Activating Token Index: 239

Text #12

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.7347. Min Act: -0.1700

Data Index: 4058279 (Open Web Text)

Max Activating Token Index: 728

Text #13

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.7562. Min Act: -0.1700

Data Index: 1925513 (Open Web Text)

Max Activating Token Index: 28

Text #14

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.7828. Min Act: -0.1700

Data Index: 6440380 (Open Web Text)

Max Activating Token Index: 423

Text #15

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.7350. Min Act: -0.1700

Data Index: 3156693 (Open Web Text)

Max Activating Token Index: 599

Text #16

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.7570. Min Act: -0.1700

Data Index: 5957873 (Open Web Text)

Max Activating Token Index: 177

Text #17

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.7217. Min Act: -0.1700

Data Index: 4663932 (Open Web Text)

Max Activating Token Index: 724

Text #18

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.7130. Min Act: -0.1700

Data Index: 1118716 (Open Web Text)

Max Activating Token Index: 108

Text #19

Max Range: 5.3541. Min Range: -5.3541

Max Act: 4.7133. Min Act: -0.1700

Data Index: 2317561 (Open Web Text)

Max Activating Token Index: 477