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

Dataset: Open Web Text

Neuron 1027 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: 2.9502. Min Range: -2.9502

Max Act: 2.9502. Min Act: -0.1700

Data Index: 7785738 (Open Web Text)

Max Activating Token Index: 11

Text #1

Max Range: 2.9502. Min Range: -2.9502

Max Act: 2.9166. Min Act: -0.1700

Data Index: 747675 (Open Web Text)

Max Activating Token Index: 16

Text #2

Max Range: 2.9502. Min Range: -2.9502

Max Act: 2.9140. Min Act: -0.1700

Data Index: 6545737 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 2.9502. Min Range: -2.9502

Max Act: 2.8482. Min Act: -0.1700

Data Index: 1596316 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 2.9502. Min Range: -2.9502

Max Act: 2.8417. Min Act: -0.1700

Data Index: 7340073 (Open Web Text)

Max Activating Token Index: 55

Text #5

Max Range: 2.9502. Min Range: -2.9502

Max Act: 2.8548. Min Act: -0.1700

Data Index: 6181624 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 2.9502. Min Range: -2.9502

Max Act: 2.8548. Min Act: -0.1700

Data Index: 3089321 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 2.9502. Min Range: -2.9502

Max Act: 2.8269. Min Act: -0.1700

Data Index: 571728 (Open Web Text)

Max Activating Token Index: 255

Text #8

Max Range: 2.9502. Min Range: -2.9502

Max Act: 2.8321. Min Act: -0.1700

Data Index: 5944378 (Open Web Text)

Max Activating Token Index: 257

Text #9

Max Range: 2.9502. Min Range: -2.9502

Max Act: 2.8027. Min Act: -0.1700

Data Index: 5281531 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 2.9502. Min Range: -2.9502

Max Act: 2.8090. Min Act: -0.1700

Data Index: 733141 (Open Web Text)

Max Activating Token Index: 30

Text #11

Max Range: 2.9502. Min Range: -2.9502

Max Act: 2.7874. Min Act: -0.1700

Data Index: 8580058 (Open Web Text)

Max Activating Token Index: 173

Text #12

Max Range: 2.9502. Min Range: -2.9502

Max Act: 2.7808. Min Act: -0.1700

Data Index: 2149654 (Open Web Text)

Max Activating Token Index: 375

Text #13

Max Range: 2.9502. Min Range: -2.9502

Max Act: 2.7825. Min Act: -0.1700

Data Index: 1505699 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 2.9502. Min Range: -2.9502

Max Act: 2.7662. Min Act: -0.1700

Data Index: 5351936 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 2.9502. Min Range: -2.9502

Max Act: 2.7709. Min Act: -0.1700

Data Index: 8536607 (Open Web Text)

Max Activating Token Index: 230

Text #16

Max Range: 2.9502. Min Range: -2.9502

Max Act: 2.7791. Min Act: -0.1700

Data Index: 1111954 (Open Web Text)

Max Activating Token Index: 72

Text #17

Max Range: 2.9502. Min Range: -2.9502

Max Act: 2.7648. Min Act: -0.1700

Data Index: 4823408 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 2.9502. Min Range: -2.9502

Max Act: 2.7745. Min Act: -0.1700

Data Index: 415439 (Open Web Text)

Max Activating Token Index: 508

Text #19

Max Range: 2.9502. Min Range: -2.9502

Max Act: 2.7723. Min Act: -0.1700

Data Index: 3969232 (Open Web Text)

Max Activating Token Index: 5