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

Dataset: Open Web Text

Neuron 1980 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: 4.5143. Min Range: -4.5143

Max Act: 4.5143. Min Act: -0.1700

Data Index: 4452630 (Open Web Text)

Max Activating Token Index: 52

Text #1

Max Range: 4.5143. Min Range: -4.5143

Max Act: 4.4535. Min Act: -0.1700

Data Index: 5127210 (Open Web Text)

Max Activating Token Index: 876

Text #2

Max Range: 4.5143. Min Range: -4.5143

Max Act: 4.4015. Min Act: -0.1700

Data Index: 7948831 (Open Web Text)

Max Activating Token Index: 627

Text #3

Max Range: 4.5143. Min Range: -4.5143

Max Act: 4.4609. Min Act: -0.1700

Data Index: 1364240 (Open Web Text)

Max Activating Token Index: 39

Text #4

Max Range: 4.5143. Min Range: -4.5143

Max Act: 4.4511. Min Act: -0.1700

Data Index: 1282564 (Open Web Text)

Max Activating Token Index: 921

Text #5

Max Range: 4.5143. Min Range: -4.5143

Max Act: 4.3738. Min Act: -0.1700

Data Index: 2086835 (Open Web Text)

Max Activating Token Index: 634

Text #6

Max Range: 4.5143. Min Range: -4.5143

Max Act: 4.3897. Min Act: -0.1700

Data Index: 5755615 (Open Web Text)

Max Activating Token Index: 212

Text #7

Max Range: 4.5143. Min Range: -4.5143

Max Act: 4.4121. Min Act: -0.1700

Data Index: 5474089 (Open Web Text)

Max Activating Token Index: 345

Text #8

Max Range: 4.5143. Min Range: -4.5143

Max Act: 4.3501. Min Act: -0.1700

Data Index: 4366500 (Open Web Text)

Max Activating Token Index: 650

Text #9

Max Range: 4.5143. Min Range: -4.5143

Max Act: 4.3708. Min Act: -0.1700

Data Index: 200934 (Open Web Text)

Max Activating Token Index: 114

Text #10

Max Range: 4.5143. Min Range: -4.5143

Max Act: 4.3539. Min Act: -0.1700

Data Index: 3776541 (Open Web Text)

Max Activating Token Index: 29

Text #11

Max Range: 4.5143. Min Range: -4.5143

Max Act: 4.3759. Min Act: -0.1700

Data Index: 8445678 (Open Web Text)

Max Activating Token Index: 204

Text #12

Max Range: 4.5143. Min Range: -4.5143

Max Act: 4.3792. Min Act: -0.1700

Data Index: 8072410 (Open Web Text)

Max Activating Token Index: 426

Text #13

Max Range: 4.5143. Min Range: -4.5143

Max Act: 4.3353. Min Act: -0.1700

Data Index: 1055520 (Open Web Text)

Max Activating Token Index: 13

Text #14

Max Range: 4.5143. Min Range: -4.5143

Max Act: 4.3444. Min Act: -0.1700

Data Index: 8194674 (Open Web Text)

Max Activating Token Index: 559

Text #15

Max Range: 4.5143. Min Range: -4.5143

Max Act: 4.3514. Min Act: -0.1700

Data Index: 5909005 (Open Web Text)

Max Activating Token Index: 470

Text #16

Max Range: 4.5143. Min Range: -4.5143

Max Act: 4.3260. Min Act: -0.1700

Data Index: 4859150 (Open Web Text)

Max Activating Token Index: 67

Text #17

Max Range: 4.5143. Min Range: -4.5143

Max Act: 4.3302. Min Act: -0.1700

Data Index: 2643581 (Open Web Text)

Max Activating Token Index: 347

Text #18

Max Range: 4.5143. Min Range: -4.5143

Max Act: 4.3636. Min Act: -0.1700

Data Index: 6419568 (Open Web Text)

Max Activating Token Index: 322

Text #19

Max Range: 4.5143. Min Range: -4.5143

Max Act: 4.3359. Min Act: -0.1700

Data Index: 7390134 (Open Web Text)

Max Activating Token Index: 421