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

Dataset: Open Web Text

Neuron 754 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: 4.8604. Min Range: -4.8604

Max Act: 4.8604. Min Act: -0.1700

Data Index: 211033 (Open Web Text)

Max Activating Token Index: 776

Text #1

Max Range: 4.8604. Min Range: -4.8604

Max Act: 4.8340. Min Act: -0.1700

Data Index: 6527385 (Open Web Text)

Max Activating Token Index: 443

Text #2

Max Range: 4.8604. Min Range: -4.8604

Max Act: 4.5094. Min Act: -0.1700

Data Index: 8778279 (Open Web Text)

Max Activating Token Index: 425

Text #3

Max Range: 4.8604. Min Range: -4.8604

Max Act: 4.4689. Min Act: -0.1700

Data Index: 7380693 (Open Web Text)

Max Activating Token Index: 359

Text #4

Max Range: 4.8604. Min Range: -4.8604

Max Act: 4.4895. Min Act: -0.1700

Data Index: 4883442 (Open Web Text)

Max Activating Token Index: 687

Text #5

Max Range: 4.8604. Min Range: -4.8604

Max Act: 4.4712. Min Act: -0.1700

Data Index: 6650227 (Open Web Text)

Max Activating Token Index: 382

Text #6

Max Range: 4.8604. Min Range: -4.8604

Max Act: 4.4419. Min Act: -0.1700

Data Index: 7155842 (Open Web Text)

Max Activating Token Index: 428

Text #7

Max Range: 4.8604. Min Range: -4.8604

Max Act: 4.4313. Min Act: -0.1700

Data Index: 4511422 (Open Web Text)

Max Activating Token Index: 706

Text #8

Max Range: 4.8604. Min Range: -4.8604

Max Act: 4.3842. Min Act: -0.1700

Data Index: 60690 (Open Web Text)

Max Activating Token Index: 720

Text #9

Max Range: 4.8604. Min Range: -4.8604

Max Act: 4.4243. Min Act: -0.1700

Data Index: 2595417 (Open Web Text)

Max Activating Token Index: 65

Text #10

Max Range: 4.8604. Min Range: -4.8604

Max Act: 4.4093. Min Act: -0.1700

Data Index: 8812167 (Open Web Text)

Max Activating Token Index: 597

Text #11

Max Range: 4.8604. Min Range: -4.8604

Max Act: 4.3512. Min Act: -0.1700

Data Index: 2785510 (Open Web Text)

Max Activating Token Index: 891

Text #12

Max Range: 4.8604. Min Range: -4.8604

Max Act: 4.3350. Min Act: -0.1700

Data Index: 3174052 (Open Web Text)

Max Activating Token Index: 985

Text #13

Max Range: 4.8604. Min Range: -4.8604

Max Act: 4.3403. Min Act: -0.1700

Data Index: 243871 (Open Web Text)

Max Activating Token Index: 130

Text #14

Max Range: 4.8604. Min Range: -4.8604

Max Act: 4.3535. Min Act: -0.1700

Data Index: 7240934 (Open Web Text)

Max Activating Token Index: 875

Text #15

Max Range: 4.8604. Min Range: -4.8604

Max Act: 4.3150. Min Act: -0.1700

Data Index: 6051277 (Open Web Text)

Max Activating Token Index: 309

Text #16

Max Range: 4.8604. Min Range: -4.8604

Max Act: 4.3459. Min Act: -0.1700

Data Index: 8691168 (Open Web Text)

Max Activating Token Index: 188

Text #17

Max Range: 4.8604. Min Range: -4.8604

Max Act: 4.3337. Min Act: -0.1700

Data Index: 5323750 (Open Web Text)

Max Activating Token Index: 280

Text #18

Max Range: 4.8604. Min Range: -4.8604

Max Act: 4.3552. Min Act: -0.1700

Data Index: 5618300 (Open Web Text)

Max Activating Token Index: 911

Text #19

Max Range: 4.8604. Min Range: -4.8604

Max Act: 4.3385. Min Act: -0.1700

Data Index: 5929797 (Open Web Text)

Max Activating Token Index: 91