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

Dataset: Open Web Text

Neuron 2681 in Layer 0

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: 4.5479. Min Range: -4.5479

Max Act: 4.5479. Min Act: -0.1700

Data Index: 7942003 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.5479. Min Range: -4.5479

Max Act: 4.5456. Min Act: -0.1700

Data Index: 1714392 (Open Web Text)

Max Activating Token Index: 958

Text #2

Max Range: 4.5479. Min Range: -4.5479

Max Act: 4.4998. Min Act: -0.1700

Data Index: 5398555 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.5479. Min Range: -4.5479

Max Act: 4.4876. Min Act: -0.1700

Data Index: 6421606 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 4.5479. Min Range: -4.5479

Max Act: 4.4741. Min Act: -0.1700

Data Index: 8264520 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.5479. Min Range: -4.5479

Max Act: 4.4598. Min Act: -0.1700

Data Index: 5322613 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.5479. Min Range: -4.5479

Max Act: 4.4590. Min Act: -0.1700

Data Index: 7316107 (Open Web Text)

Max Activating Token Index: 811

Text #7

Max Range: 4.5479. Min Range: -4.5479

Max Act: 4.4493. Min Act: -0.1700

Data Index: 3355463 (Open Web Text)

Max Activating Token Index: 901

Text #8

Max Range: 4.5479. Min Range: -4.5479

Max Act: 4.4489. Min Act: -0.1700

Data Index: 762483 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.5479. Min Range: -4.5479

Max Act: 4.4570. Min Act: -0.1700

Data Index: 6435038 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 4.5479. Min Range: -4.5479

Max Act: 4.4226. Min Act: -0.1700

Data Index: 7405099 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 4.5479. Min Range: -4.5479

Max Act: 4.4172. Min Act: -0.1700

Data Index: 2049659 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 4.5479. Min Range: -4.5479

Max Act: 4.4153. Min Act: -0.1700

Data Index: 7343717 (Open Web Text)

Max Activating Token Index: 21

Text #13

Max Range: 4.5479. Min Range: -4.5479

Max Act: 4.4209. Min Act: -0.1700

Data Index: 7231255 (Open Web Text)

Max Activating Token Index: 10

Text #14

Max Range: 4.5479. Min Range: -4.5479

Max Act: 4.4425. Min Act: -0.1700

Data Index: 737521 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 4.5479. Min Range: -4.5479

Max Act: 4.4331. Min Act: -0.1700

Data Index: 6106692 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 4.5479. Min Range: -4.5479

Max Act: 4.4231. Min Act: -0.1700

Data Index: 3231245 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.5479. Min Range: -4.5479

Max Act: 4.4364. Min Act: -0.1700

Data Index: 6046930 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 4.5479. Min Range: -4.5479

Max Act: 4.4279. Min Act: -0.1700

Data Index: 661583 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.5479. Min Range: -4.5479

Max Act: 4.4352. Min Act: -0.1700

Data Index: 2217944 (Open Web Text)

Max Activating Token Index: 5