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

Dataset: Open Web Text

Neuron 1470 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: 3.4793. Min Range: -3.4793

Max Act: 3.4793. Min Act: -0.1700

Data Index: 4868890 (Open Web Text)

Max Activating Token Index: 470

Text #1

Max Range: 3.4793. Min Range: -3.4793

Max Act: 3.4182. Min Act: -0.1700

Data Index: 7611988 (Open Web Text)

Max Activating Token Index: 504

Text #2

Max Range: 3.4793. Min Range: -3.4793

Max Act: 3.4075. Min Act: -0.1700

Data Index: 1649988 (Open Web Text)

Max Activating Token Index: 239

Text #3

Max Range: 3.4793. Min Range: -3.4793

Max Act: 3.3633. Min Act: -0.1700

Data Index: 428902 (Open Web Text)

Max Activating Token Index: 74

Text #4

Max Range: 3.4793. Min Range: -3.4793

Max Act: 3.3210. Min Act: -0.1700

Data Index: 1867822 (Open Web Text)

Max Activating Token Index: 631

Text #5

Max Range: 3.4793. Min Range: -3.4793

Max Act: 3.3307. Min Act: -0.1700

Data Index: 289725 (Open Web Text)

Max Activating Token Index: 366

Text #6

Max Range: 3.4793. Min Range: -3.4793

Max Act: 3.3341. Min Act: -0.1700

Data Index: 6882904 (Open Web Text)

Max Activating Token Index: 229

Text #7

Max Range: 3.4793. Min Range: -3.4793

Max Act: 3.2983. Min Act: -0.1700

Data Index: 1662302 (Open Web Text)

Max Activating Token Index: 667

Text #8

Max Range: 3.4793. Min Range: -3.4793

Max Act: 3.2782. Min Act: -0.1700

Data Index: 4315773 (Open Web Text)

Max Activating Token Index: 815

Text #9

Max Range: 3.4793. Min Range: -3.4793

Max Act: 3.2799. Min Act: -0.1700

Data Index: 2924335 (Open Web Text)

Max Activating Token Index: 419

Text #10

Max Range: 3.4793. Min Range: -3.4793

Max Act: 3.2890. Min Act: -0.1700

Data Index: 8000142 (Open Web Text)

Max Activating Token Index: 600

Text #11

Max Range: 3.4793. Min Range: -3.4793

Max Act: 3.2759. Min Act: -0.1700

Data Index: 7202879 (Open Web Text)

Max Activating Token Index: 482

Text #12

Max Range: 3.4793. Min Range: -3.4793

Max Act: 3.2801. Min Act: -0.1700

Data Index: 7177353 (Open Web Text)

Max Activating Token Index: 54

Text #13

Max Range: 3.4793. Min Range: -3.4793

Max Act: 3.2770. Min Act: -0.1700

Data Index: 5976917 (Open Web Text)

Max Activating Token Index: 567

Text #14

Max Range: 3.4793. Min Range: -3.4793

Max Act: 3.2593. Min Act: -0.1700

Data Index: 4697671 (Open Web Text)

Max Activating Token Index: 782

Text #15

Max Range: 3.4793. Min Range: -3.4793

Max Act: 3.2598. Min Act: -0.1700

Data Index: 2167515 (Open Web Text)

Max Activating Token Index: 371

Text #16

Max Range: 3.4793. Min Range: -3.4793

Max Act: 3.2542. Min Act: -0.1700

Data Index: 3220352 (Open Web Text)

Max Activating Token Index: 174

Text #17

Max Range: 3.4793. Min Range: -3.4793

Max Act: 3.2624. Min Act: -0.1700

Data Index: 3169697 (Open Web Text)

Max Activating Token Index: 376

Text #18

Max Range: 3.4793. Min Range: -3.4793

Max Act: 3.2655. Min Act: -0.1700

Data Index: 7530931 (Open Web Text)

Max Activating Token Index: 859

Text #19

Max Range: 3.4793. Min Range: -3.4793

Max Act: 3.2654. Min Act: -0.1700

Data Index: 5020096 (Open Web Text)

Max Activating Token Index: 73