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

Dataset: Open Web Text

Neuron 556 in Layer 2

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: 4.3966. Min Range: -4.3966

Max Act: 4.3966. Min Act: -0.1700

Data Index: 2770337 (Open Web Text)

Max Activating Token Index: 454

Text #1

Max Range: 4.3966. Min Range: -4.3966

Max Act: 4.3886. Min Act: -0.1700

Data Index: 6652423 (Open Web Text)

Max Activating Token Index: 88

Text #2

Max Range: 4.3966. Min Range: -4.3966

Max Act: 4.3561. Min Act: -0.1700

Data Index: 7518974 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 4.3966. Min Range: -4.3966

Max Act: 4.3459. Min Act: -0.1700

Data Index: 4908614 (Open Web Text)

Max Activating Token Index: 527

Text #4

Max Range: 4.3966. Min Range: -4.3966

Max Act: 4.3401. Min Act: -0.1700

Data Index: 5527763 (Open Web Text)

Max Activating Token Index: 405

Text #5

Max Range: 4.3966. Min Range: -4.3966

Max Act: 4.2635. Min Act: -0.1700

Data Index: 31389 (Open Web Text)

Max Activating Token Index: 133

Text #6

Max Range: 4.3966. Min Range: -4.3966

Max Act: 4.2733. Min Act: -0.1700

Data Index: 3629565 (Open Web Text)

Max Activating Token Index: 107

Text #7

Max Range: 4.3966. Min Range: -4.3966

Max Act: 4.2982. Min Act: -0.1700

Data Index: 491548 (Open Web Text)

Max Activating Token Index: 101

Text #8

Max Range: 4.3966. Min Range: -4.3966

Max Act: 4.2803. Min Act: -0.1700

Data Index: 398108 (Open Web Text)

Max Activating Token Index: 84

Text #9

Max Range: 4.3966. Min Range: -4.3966

Max Act: 4.3028. Min Act: -0.1700

Data Index: 6129579 (Open Web Text)

Max Activating Token Index: 221

Text #10

Max Range: 4.3966. Min Range: -4.3966

Max Act: 4.3094. Min Act: -0.1700

Data Index: 6474311 (Open Web Text)

Max Activating Token Index: 37

Text #11

Max Range: 4.3966. Min Range: -4.3966

Max Act: 4.3228. Min Act: -0.1700

Data Index: 8557078 (Open Web Text)

Max Activating Token Index: 253

Text #12

Max Range: 4.3966. Min Range: -4.3966

Max Act: 4.3241. Min Act: -0.1700

Data Index: 1383363 (Open Web Text)

Max Activating Token Index: 276

Text #13

Max Range: 4.3966. Min Range: -4.3966

Max Act: 4.2911. Min Act: -0.1700

Data Index: 8033130 (Open Web Text)

Max Activating Token Index: 44

Text #14

Max Range: 4.3966. Min Range: -4.3966

Max Act: 4.3003. Min Act: -0.1700

Data Index: 3232776 (Open Web Text)

Max Activating Token Index: 481

Text #15

Max Range: 4.3966. Min Range: -4.3966

Max Act: 4.2525. Min Act: -0.1700

Data Index: 6849873 (Open Web Text)

Max Activating Token Index: 313

Text #16

Max Range: 4.3966. Min Range: -4.3966

Max Act: 4.2241. Min Act: -0.1700

Data Index: 7282825 (Open Web Text)

Max Activating Token Index: 418

Text #17

Max Range: 4.3966. Min Range: -4.3966

Max Act: 4.2559. Min Act: -0.1700

Data Index: 6717800 (Open Web Text)

Max Activating Token Index: 65

Text #18

Max Range: 4.3966. Min Range: -4.3966

Max Act: 4.2658. Min Act: -0.1700

Data Index: 487617 (Open Web Text)

Max Activating Token Index: 860

Text #19

Max Range: 4.3966. Min Range: -4.3966

Max Act: 4.2395. Min Act: -0.1700

Data Index: 3618714 (Open Web Text)

Max Activating Token Index: 15