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

Dataset: Open Web Text

Neuron 81 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: 4.4459. Min Range: -4.4459

Max Act: 4.4459. Min Act: -0.1700

Data Index: 6707589 (Open Web Text)

Max Activating Token Index: 769

Text #1

Max Range: 4.4459. Min Range: -4.4459

Max Act: 4.3976. Min Act: -0.1700

Data Index: 4165351 (Open Web Text)

Max Activating Token Index: 436

Text #2

Max Range: 4.4459. Min Range: -4.4459

Max Act: 4.4184. Min Act: -0.1700

Data Index: 1310232 (Open Web Text)

Max Activating Token Index: 718

Text #3

Max Range: 4.4459. Min Range: -4.4459

Max Act: 4.3835. Min Act: -0.1700

Data Index: 4590657 (Open Web Text)

Max Activating Token Index: 868

Text #4

Max Range: 4.4459. Min Range: -4.4459

Max Act: 4.3591. Min Act: -0.1700

Data Index: 3913004 (Open Web Text)

Max Activating Token Index: 468

Text #5

Max Range: 4.4459. Min Range: -4.4459

Max Act: 4.3699. Min Act: -0.1700

Data Index: 1561403 (Open Web Text)

Max Activating Token Index: 846

Text #6

Max Range: 4.4459. Min Range: -4.4459

Max Act: 4.3580. Min Act: -0.1700

Data Index: 1550943 (Open Web Text)

Max Activating Token Index: 603

Text #7

Max Range: 4.4459. Min Range: -4.4459

Max Act: 4.3505. Min Act: -0.1700

Data Index: 2507471 (Open Web Text)

Max Activating Token Index: 564

Text #8

Max Range: 4.4459. Min Range: -4.4459

Max Act: 4.3684. Min Act: -0.1700

Data Index: 5057625 (Open Web Text)

Max Activating Token Index: 304

Text #9

Max Range: 4.4459. Min Range: -4.4459

Max Act: 4.3585. Min Act: -0.1700

Data Index: 4634554 (Open Web Text)

Max Activating Token Index: 600

Text #10

Max Range: 4.4459. Min Range: -4.4459

Max Act: 4.3504. Min Act: -0.1700

Data Index: 1813197 (Open Web Text)

Max Activating Token Index: 884

Text #11

Max Range: 4.4459. Min Range: -4.4459

Max Act: 4.3341. Min Act: -0.1700

Data Index: 5322689 (Open Web Text)

Max Activating Token Index: 373

Text #12

Max Range: 4.4459. Min Range: -4.4459

Max Act: 4.3242. Min Act: -0.1700

Data Index: 2266652 (Open Web Text)

Max Activating Token Index: 394

Text #13

Max Range: 4.4459. Min Range: -4.4459

Max Act: 4.3101. Min Act: -0.1700

Data Index: 1336678 (Open Web Text)

Max Activating Token Index: 996

Text #14

Max Range: 4.4459. Min Range: -4.4459

Max Act: 4.3148. Min Act: -0.1700

Data Index: 2415328 (Open Web Text)

Max Activating Token Index: 528

Text #15

Max Range: 4.4459. Min Range: -4.4459

Max Act: 4.3343. Min Act: -0.1700

Data Index: 5400007 (Open Web Text)

Max Activating Token Index: 753

Text #16

Max Range: 4.4459. Min Range: -4.4459

Max Act: 4.3240. Min Act: -0.1700

Data Index: 5481512 (Open Web Text)

Max Activating Token Index: 993

Text #17

Max Range: 4.4459. Min Range: -4.4459

Max Act: 4.3207. Min Act: -0.1700

Data Index: 2417405 (Open Web Text)

Max Activating Token Index: 707

Text #18

Max Range: 4.4459. Min Range: -4.4459

Max Act: 4.3470. Min Act: -0.1700

Data Index: 1918618 (Open Web Text)

Max Activating Token Index: 1004

Text #19

Max Range: 4.4459. Min Range: -4.4459

Max Act: 4.3304. Min Act: -0.1700

Data Index: 6485636 (Open Web Text)

Max Activating Token Index: 530