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

Dataset: Open Web Text

Neuron 139 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: 3.5498. Min Range: -3.5498

Max Act: 3.5498. Min Act: -0.1700

Data Index: 8509417 (Open Web Text)

Max Activating Token Index: 457

Text #1

Max Range: 3.5498. Min Range: -3.5498

Max Act: 3.4869. Min Act: -0.1700

Data Index: 6647336 (Open Web Text)

Max Activating Token Index: 450

Text #2

Max Range: 3.5498. Min Range: -3.5498

Max Act: 3.4434. Min Act: -0.1700

Data Index: 1984743 (Open Web Text)

Max Activating Token Index: 706

Text #3

Max Range: 3.5498. Min Range: -3.5498

Max Act: 3.4665. Min Act: -0.1700

Data Index: 7014082 (Open Web Text)

Max Activating Token Index: 765

Text #4

Max Range: 3.5498. Min Range: -3.5498

Max Act: 3.4407. Min Act: -0.1700

Data Index: 7646417 (Open Web Text)

Max Activating Token Index: 585

Text #5

Max Range: 3.5498. Min Range: -3.5498

Max Act: 3.4639. Min Act: -0.1700

Data Index: 1637964 (Open Web Text)

Max Activating Token Index: 879

Text #6

Max Range: 3.5498. Min Range: -3.5498

Max Act: 3.4462. Min Act: -0.1700

Data Index: 2237780 (Open Web Text)

Max Activating Token Index: 719

Text #7

Max Range: 3.5498. Min Range: -3.5498

Max Act: 3.4526. Min Act: -0.1700

Data Index: 1672783 (Open Web Text)

Max Activating Token Index: 504

Text #8

Max Range: 3.5498. Min Range: -3.5498

Max Act: 3.4193. Min Act: -0.1700

Data Index: 4973770 (Open Web Text)

Max Activating Token Index: 944

Text #9

Max Range: 3.5498. Min Range: -3.5498

Max Act: 3.4302. Min Act: -0.1700

Data Index: 1132117 (Open Web Text)

Max Activating Token Index: 863

Text #10

Max Range: 3.5498. Min Range: -3.5498

Max Act: 3.4011. Min Act: -0.1700

Data Index: 5794232 (Open Web Text)

Max Activating Token Index: 328

Text #11

Max Range: 3.5498. Min Range: -3.5498

Max Act: 3.4184. Min Act: -0.1700

Data Index: 4375142 (Open Web Text)

Max Activating Token Index: 545

Text #12

Max Range: 3.5498. Min Range: -3.5498

Max Act: 3.4234. Min Act: -0.1700

Data Index: 2098086 (Open Web Text)

Max Activating Token Index: 693

Text #13

Max Range: 3.5498. Min Range: -3.5498

Max Act: 3.3993. Min Act: -0.1700

Data Index: 3039350 (Open Web Text)

Max Activating Token Index: 324

Text #14

Max Range: 3.5498. Min Range: -3.5498

Max Act: 3.3961. Min Act: -0.1700

Data Index: 5526590 (Open Web Text)

Max Activating Token Index: 196

Text #15

Max Range: 3.5498. Min Range: -3.5498

Max Act: 3.3982. Min Act: -0.1700

Data Index: 6117386 (Open Web Text)

Max Activating Token Index: 678

Text #16

Max Range: 3.5498. Min Range: -3.5498

Max Act: 3.3940. Min Act: -0.1700

Data Index: 3618981 (Open Web Text)

Max Activating Token Index: 233

Text #17

Max Range: 3.5498. Min Range: -3.5498

Max Act: 3.3696. Min Act: -0.1700

Data Index: 2118202 (Open Web Text)

Max Activating Token Index: 429

Text #18

Max Range: 3.5498. Min Range: -3.5498

Max Act: 3.3646. Min Act: -0.1700

Data Index: 2189019 (Open Web Text)

Max Activating Token Index: 960

Text #19

Max Range: 3.5498. Min Range: -3.5498

Max Act: 3.3797. Min Act: -0.1700

Data Index: 7409542 (Open Web Text)

Max Activating Token Index: 690