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

Dataset: Open Web Text

Neuron 176 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: 1.6020. Min Range: -1.6020

Max Act: 1.6020. Min Act: -0.1700

Data Index: 262979 (Open Web Text)

Max Activating Token Index: 479

Text #1

Max Range: 1.6020. Min Range: -1.6020

Max Act: 1.5669. Min Act: -0.1700

Data Index: 7905168 (Open Web Text)

Max Activating Token Index: 150

Text #2

Max Range: 1.6020. Min Range: -1.6020

Max Act: 1.5745. Min Act: -0.1700

Data Index: 2153208 (Open Web Text)

Max Activating Token Index: 48

Text #3

Max Range: 1.6020. Min Range: -1.6020

Max Act: 1.5546. Min Act: -0.1700

Data Index: 3222966 (Open Web Text)

Max Activating Token Index: 130

Text #4

Max Range: 1.6020. Min Range: -1.6020

Max Act: 1.5527. Min Act: -0.1700

Data Index: 6549991 (Open Web Text)

Max Activating Token Index: 434

Text #5

Max Range: 1.6020. Min Range: -1.6020

Max Act: 1.5558. Min Act: -0.1660

Data Index: 7066811 (Open Web Text)

Max Activating Token Index: 234

Text #6

Max Range: 1.6020. Min Range: -1.6020

Max Act: 1.5636. Min Act: -0.1700

Data Index: 500222 (Open Web Text)

Max Activating Token Index: 842

Text #7

Max Range: 1.6020. Min Range: -1.6020

Max Act: 1.5553. Min Act: -0.1700

Data Index: 8194957 (Open Web Text)

Max Activating Token Index: 208

Text #8

Max Range: 1.6020. Min Range: -1.6020

Max Act: 1.5468. Min Act: -0.1700

Data Index: 3062608 (Open Web Text)

Max Activating Token Index: 599

Text #9

Max Range: 1.6020. Min Range: -1.6020

Max Act: 1.5391. Min Act: -0.1700

Data Index: 1542470 (Open Web Text)

Max Activating Token Index: 869

Text #10

Max Range: 1.6020. Min Range: -1.6020

Max Act: 1.5411. Min Act: -0.1700

Data Index: 5451148 (Open Web Text)

Max Activating Token Index: 73

Text #11

Max Range: 1.6020. Min Range: -1.6020

Max Act: 1.5364. Min Act: -0.1700

Data Index: 229296 (Open Web Text)

Max Activating Token Index: 536

Text #12

Max Range: 1.6020. Min Range: -1.6020

Max Act: 1.5327. Min Act: -0.1700

Data Index: 7324863 (Open Web Text)

Max Activating Token Index: 108

Text #13

Max Range: 1.6020. Min Range: -1.6020

Max Act: 1.5300. Min Act: -0.1700

Data Index: 4741963 (Open Web Text)

Max Activating Token Index: 20

Text #14

Max Range: 1.6020. Min Range: -1.6020

Max Act: 1.5356. Min Act: -0.1700

Data Index: 603850 (Open Web Text)

Max Activating Token Index: 394

Text #15

Max Range: 1.6020. Min Range: -1.6020

Max Act: 1.5491. Min Act: -0.1700

Data Index: 186561 (Open Web Text)

Max Activating Token Index: 490

Text #16

Max Range: 1.6020. Min Range: -1.6020

Max Act: 1.5362. Min Act: -0.1700

Data Index: 4441699 (Open Web Text)

Max Activating Token Index: 968

Text #17

Max Range: 1.6020. Min Range: -1.6020

Max Act: 1.5265. Min Act: -0.1700

Data Index: 2327737 (Open Web Text)

Max Activating Token Index: 423

Text #18

Max Range: 1.6020. Min Range: -1.6020

Max Act: 1.5279. Min Act: -0.1700

Data Index: 4224122 (Open Web Text)

Max Activating Token Index: 542

Text #19

Max Range: 1.6020. Min Range: -1.6020

Max Act: 1.5343. Min Act: -0.1700

Data Index: 3298889 (Open Web Text)

Max Activating Token Index: 792