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

Dataset: Open Web Text

Neuron 1880 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: 3.7615. Min Range: -3.7615

Max Act: 3.7615. Min Act: -0.1700

Data Index: 5914357 (Open Web Text)

Max Activating Token Index: 958

Text #1

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.7293. Min Act: -0.1700

Data Index: 1762901 (Open Web Text)

Max Activating Token Index: 486

Text #2

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.7149. Min Act: -0.1700

Data Index: 8795213 (Open Web Text)

Max Activating Token Index: 60

Text #3

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.7294. Min Act: -0.1700

Data Index: 8071371 (Open Web Text)

Max Activating Token Index: 615

Text #4

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.7066. Min Act: -0.1700

Data Index: 7093980 (Open Web Text)

Max Activating Token Index: 98

Text #5

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.7089. Min Act: -0.1700

Data Index: 6791496 (Open Web Text)

Max Activating Token Index: 50

Text #6

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.6729. Min Act: -0.1700

Data Index: 6234995 (Open Web Text)

Max Activating Token Index: 530

Text #7

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.6777. Min Act: -0.1700

Data Index: 3009774 (Open Web Text)

Max Activating Token Index: 526

Text #8

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.6444. Min Act: -0.1700

Data Index: 4800682 (Open Web Text)

Max Activating Token Index: 1018

Text #9

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.6533. Min Act: -0.1700

Data Index: 6610303 (Open Web Text)

Max Activating Token Index: 74

Text #10

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.6430. Min Act: -0.1700

Data Index: 2480812 (Open Web Text)

Max Activating Token Index: 120

Text #11

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.6506. Min Act: -0.1700

Data Index: 2743454 (Open Web Text)

Max Activating Token Index: 465

Text #12

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.6533. Min Act: -0.1700

Data Index: 2952254 (Open Web Text)

Max Activating Token Index: 355

Text #13

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.6398. Min Act: -0.1700

Data Index: 1271186 (Open Web Text)

Max Activating Token Index: 951

Text #14

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.6148. Min Act: -0.1700

Data Index: 5887902 (Open Web Text)

Max Activating Token Index: 490

Text #15

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.6167. Min Act: -0.1700

Data Index: 925884 (Open Web Text)

Max Activating Token Index: 17

Text #16

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.6009. Min Act: -0.1700

Data Index: 3122909 (Open Web Text)

Max Activating Token Index: 496

Text #17

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.6136. Min Act: -0.1700

Data Index: 5494969 (Open Web Text)

Max Activating Token Index: 511

Text #18

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.6446. Min Act: -0.1700

Data Index: 5488854 (Open Web Text)

Max Activating Token Index: 27

Text #19

Max Range: 3.7615. Min Range: -3.7615

Max Act: 3.6193. Min Act: -0.1700

Data Index: 4514992 (Open Web Text)

Max Activating Token Index: 963