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

Dataset: Open Web Text

Neuron 159 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: 4.6257. Min Range: -4.6257

Max Act: 4.6257. Min Act: -0.1700

Data Index: 8791508 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.6257. Min Range: -4.6257

Max Act: 4.6028. Min Act: -0.1700

Data Index: 7582091 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.6257. Min Range: -4.6257

Max Act: 4.5680. Min Act: -0.1700

Data Index: 5013511 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.6257. Min Range: -4.6257

Max Act: 4.5645. Min Act: -0.1700

Data Index: 839217 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.6257. Min Range: -4.6257

Max Act: 4.4762. Min Act: -0.1700

Data Index: 3874295 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 4.6257. Min Range: -4.6257

Max Act: 4.4759. Min Act: -0.1700

Data Index: 7738469 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.6257. Min Range: -4.6257

Max Act: 4.4741. Min Act: -0.1700

Data Index: 437537 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 4.6257. Min Range: -4.6257

Max Act: 4.4679. Min Act: -0.1700

Data Index: 5740129 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.6257. Min Range: -4.6257

Max Act: 4.4951. Min Act: -0.1700

Data Index: 4993201 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.6257. Min Range: -4.6257

Max Act: 4.5006. Min Act: -0.1700

Data Index: 4772443 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 4.6257. Min Range: -4.6257

Max Act: 4.4751. Min Act: -0.1700

Data Index: 2860576 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.6257. Min Range: -4.6257

Max Act: 4.4788. Min Act: -0.1700

Data Index: 7556679 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 4.6257. Min Range: -4.6257

Max Act: 4.4767. Min Act: -0.1700

Data Index: 8720065 (Open Web Text)

Max Activating Token Index: 11

Text #13

Max Range: 4.6257. Min Range: -4.6257

Max Act: 4.4744. Min Act: -0.1700

Data Index: 7355503 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.6257. Min Range: -4.6257

Max Act: 4.4617. Min Act: -0.1700

Data Index: 1231579 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.6257. Min Range: -4.6257

Max Act: 4.4437. Min Act: -0.1700

Data Index: 4850680 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 4.6257. Min Range: -4.6257

Max Act: 4.4428. Min Act: -0.1700

Data Index: 3827952 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.6257. Min Range: -4.6257

Max Act: 4.4528. Min Act: -0.1700

Data Index: 896028 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 4.6257. Min Range: -4.6257

Max Act: 4.4567. Min Act: -0.1700

Data Index: 8121744 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.6257. Min Range: -4.6257

Max Act: 4.4492. Min Act: -0.1700

Data Index: 6995367 (Open Web Text)

Max Activating Token Index: 5