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

Dataset: Open Web Text

Neuron 1826 in Layer 4

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: 3.6424. Min Range: -3.6424

Max Act: 3.6424. Min Act: -0.1700

Data Index: 6921817 (Open Web Text)

Max Activating Token Index: 706

Text #1

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.5248. Min Act: -0.1700

Data Index: 7812914 (Open Web Text)

Max Activating Token Index: 649

Text #2

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.5238. Min Act: -0.1700

Data Index: 315284 (Open Web Text)

Max Activating Token Index: 209

Text #3

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.5147. Min Act: -0.1700

Data Index: 5863733 (Open Web Text)

Max Activating Token Index: 928

Text #4

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.5197. Min Act: -0.1700

Data Index: 929315 (Open Web Text)

Max Activating Token Index: 519

Text #5

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.5126. Min Act: -0.1700

Data Index: 595581 (Open Web Text)

Max Activating Token Index: 238

Text #6

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.4944. Min Act: -0.1700

Data Index: 6323485 (Open Web Text)

Max Activating Token Index: 472

Text #7

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.4947. Min Act: -0.1700

Data Index: 1121361 (Open Web Text)

Max Activating Token Index: 307

Text #8

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.4766. Min Act: -0.1700

Data Index: 1138847 (Open Web Text)

Max Activating Token Index: 279

Text #9

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.4899. Min Act: -0.1700

Data Index: 6862511 (Open Web Text)

Max Activating Token Index: 113

Text #10

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.4854. Min Act: -0.1700

Data Index: 8761062 (Open Web Text)

Max Activating Token Index: 472

Text #11

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.4743. Min Act: -0.1700

Data Index: 526198 (Open Web Text)

Max Activating Token Index: 67

Text #12

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.4556. Min Act: -0.1700

Data Index: 5309823 (Open Web Text)

Max Activating Token Index: 178

Text #13

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.4596. Min Act: -0.1700

Data Index: 7080648 (Open Web Text)

Max Activating Token Index: 575

Text #14

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.4692. Min Act: -0.1700

Data Index: 6773134 (Open Web Text)

Max Activating Token Index: 846

Text #15

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.4589. Min Act: -0.1700

Data Index: 4253825 (Open Web Text)

Max Activating Token Index: 908

Text #16

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.4607. Min Act: -0.1700

Data Index: 7427487 (Open Web Text)

Max Activating Token Index: 511

Text #17

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.4620. Min Act: -0.1700

Data Index: 7478090 (Open Web Text)

Max Activating Token Index: 683

Text #18

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.4461. Min Act: -0.1700

Data Index: 1476328 (Open Web Text)

Max Activating Token Index: 175

Text #19

Max Range: 3.6424. Min Range: -3.6424

Max Act: 3.4416. Min Act: -0.1700

Data Index: 645777 (Open Web Text)

Max Activating Token Index: 906