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

Dataset: Open Web Text

Neuron 1528 in Layer 3

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: 3.7605. Min Range: -3.7605

Max Act: 3.7565. Min Act: -0.1700

Data Index: 8381055 (Open Web Text)

Max Activating Token Index: 172

Text #1

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.7475. Min Act: -0.1700

Data Index: 5978389 (Open Web Text)

Max Activating Token Index: 181

Text #2

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.7414. Min Act: -0.1700

Data Index: 3120004 (Open Web Text)

Max Activating Token Index: 821

Text #3

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.6747. Min Act: -0.1700

Data Index: 7501783 (Open Web Text)

Max Activating Token Index: 499

Text #4

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.7605. Min Act: -0.1700

Data Index: 7464855 (Open Web Text)

Max Activating Token Index: 646

Text #5

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.7392. Min Act: -0.1700

Data Index: 6892041 (Open Web Text)

Max Activating Token Index: 334

Text #6

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.7220. Min Act: -0.1700

Data Index: 4174473 (Open Web Text)

Max Activating Token Index: 476

Text #7

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.7229. Min Act: -0.1700

Data Index: 1990788 (Open Web Text)

Max Activating Token Index: 779

Text #8

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.6934. Min Act: -0.1700

Data Index: 6864860 (Open Web Text)

Max Activating Token Index: 843

Text #9

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.7141. Min Act: -0.1700

Data Index: 996666 (Open Web Text)

Max Activating Token Index: 282

Text #10

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.6538. Min Act: -0.1700

Data Index: 3474088 (Open Web Text)

Max Activating Token Index: 182

Text #11

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.7051. Min Act: -0.1700

Data Index: 6520926 (Open Web Text)

Max Activating Token Index: 192

Text #12

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.6527. Min Act: -0.1700

Data Index: 6947992 (Open Web Text)

Max Activating Token Index: 716

Text #13

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.6645. Min Act: -0.1700

Data Index: 7139454 (Open Web Text)

Max Activating Token Index: 479

Text #14

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.6725. Min Act: -0.1700

Data Index: 474991 (Open Web Text)

Max Activating Token Index: 853

Text #15

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.6555. Min Act: -0.1700

Data Index: 4743242 (Open Web Text)

Max Activating Token Index: 381

Text #16

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.6992. Min Act: -0.1700

Data Index: 2143973 (Open Web Text)

Max Activating Token Index: 270

Text #17

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.6629. Min Act: -0.1700

Data Index: 297107 (Open Web Text)

Max Activating Token Index: 441

Text #18

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.6920. Min Act: -0.1700

Data Index: 5006663 (Open Web Text)

Max Activating Token Index: 137

Text #19

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.6685. Min Act: -0.1700

Data Index: 2977632 (Open Web Text)

Max Activating Token Index: 636