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

Dataset: Open Web Text

Neuron 2197 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: 4.6892. Min Range: -4.6892

Max Act: 4.6892. Min Act: -0.1700

Data Index: 8612968 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.6892. Min Range: -4.6892

Max Act: 4.6619. Min Act: -0.1700

Data Index: 2152322 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 4.6892. Min Range: -4.6892

Max Act: 4.6468. Min Act: -0.1700

Data Index: 5970683 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.6892. Min Range: -4.6892

Max Act: 4.5783. Min Act: -0.1700

Data Index: 439061 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 4.6892. Min Range: -4.6892

Max Act: 4.5709. Min Act: -0.1700

Data Index: 1634618 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 4.6892. Min Range: -4.6892

Max Act: 4.5491. Min Act: -0.1700

Data Index: 845850 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.6892. Min Range: -4.6892

Max Act: 4.5369. Min Act: -0.1700

Data Index: 774668 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 4.6892. Min Range: -4.6892

Max Act: 4.5608. Min Act: -0.1700

Data Index: 4922604 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.6892. Min Range: -4.6892

Max Act: 4.5306. Min Act: -0.1700

Data Index: 525205 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.6892. Min Range: -4.6892

Max Act: 4.5172. Min Act: -0.1700

Data Index: 5838302 (Open Web Text)

Max Activating Token Index: 11

Text #10

Max Range: 4.6892. Min Range: -4.6892

Max Act: 4.5049. Min Act: -0.1700

Data Index: 6289517 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 4.6892. Min Range: -4.6892

Max Act: 4.4824. Min Act: -0.1700

Data Index: 5117683 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 4.6892. Min Range: -4.6892

Max Act: 4.4903. Min Act: -0.1700

Data Index: 812216 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 4.6892. Min Range: -4.6892

Max Act: 4.4936. Min Act: -0.1700

Data Index: 2333394 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 4.6892. Min Range: -4.6892

Max Act: 4.4480. Min Act: -0.1700

Data Index: 3217792 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 4.6892. Min Range: -4.6892

Max Act: 4.4656. Min Act: -0.1700

Data Index: 5731019 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.6892. Min Range: -4.6892

Max Act: 4.4432. Min Act: -0.1700

Data Index: 5821723 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.6892. Min Range: -4.6892

Max Act: 4.4634. Min Act: -0.1700

Data Index: 3346273 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 4.6892. Min Range: -4.6892

Max Act: 4.4722. Min Act: -0.1700

Data Index: 3509500 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.6892. Min Range: -4.6892

Max Act: 4.4716. Min Act: -0.1700

Data Index: 564985 (Open Web Text)

Max Activating Token Index: 4