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

Dataset: Open Web Text

Neuron 496 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: 3.7966. Min Range: -3.7966

Max Act: 3.7966. Min Act: -0.1700

Data Index: 1165391 (Open Web Text)

Max Activating Token Index: 479

Text #1

Max Range: 3.7966. Min Range: -3.7966

Max Act: 3.7507. Min Act: -0.1700

Data Index: 5457797 (Open Web Text)

Max Activating Token Index: 105

Text #2

Max Range: 3.7966. Min Range: -3.7966

Max Act: 3.7522. Min Act: -0.1700

Data Index: 2230065 (Open Web Text)

Max Activating Token Index: 647

Text #3

Max Range: 3.7966. Min Range: -3.7966

Max Act: 3.6002. Min Act: -0.1700

Data Index: 3747511 (Open Web Text)

Max Activating Token Index: 94

Text #4

Max Range: 3.7966. Min Range: -3.7966

Max Act: 3.5674. Min Act: -0.1700

Data Index: 5285419 (Open Web Text)

Max Activating Token Index: 823

Text #5

Max Range: 3.7966. Min Range: -3.7966

Max Act: 3.5715. Min Act: -0.1700

Data Index: 4514240 (Open Web Text)

Max Activating Token Index: 131

Text #6

Max Range: 3.7966. Min Range: -3.7966

Max Act: 3.5766. Min Act: -0.1700

Data Index: 8340352 (Open Web Text)

Max Activating Token Index: 21

Text #7

Max Range: 3.7966. Min Range: -3.7966

Max Act: 3.5290. Min Act: -0.1700

Data Index: 4800987 (Open Web Text)

Max Activating Token Index: 43

Text #8

Max Range: 3.7966. Min Range: -3.7966

Max Act: 3.5249. Min Act: -0.1700

Data Index: 7319250 (Open Web Text)

Max Activating Token Index: 359

Text #9

Max Range: 3.7966. Min Range: -3.7966

Max Act: 3.4920. Min Act: -0.1700

Data Index: 1336274 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.7966. Min Range: -3.7966

Max Act: 3.4701. Min Act: -0.1700

Data Index: 2894612 (Open Web Text)

Max Activating Token Index: 1009

Text #11

Max Range: 3.7966. Min Range: -3.7966

Max Act: 3.4920. Min Act: -0.1700

Data Index: 8226104 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.7966. Min Range: -3.7966

Max Act: 3.4920. Min Act: -0.1700

Data Index: 7632980 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.7966. Min Range: -3.7966

Max Act: 3.5370. Min Act: -0.1700

Data Index: 3942340 (Open Web Text)

Max Activating Token Index: 970

Text #14

Max Range: 3.7966. Min Range: -3.7966

Max Act: 3.4776. Min Act: -0.1700

Data Index: 7012066 (Open Web Text)

Max Activating Token Index: 240

Text #15

Max Range: 3.7966. Min Range: -3.7966

Max Act: 3.4920. Min Act: -0.1700

Data Index: 3479151 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.7966. Min Range: -3.7966

Max Act: 3.4950. Min Act: -0.1700

Data Index: 6816315 (Open Web Text)

Max Activating Token Index: 540

Text #17

Max Range: 3.7966. Min Range: -3.7966

Max Act: 3.4920. Min Act: -0.1700

Data Index: 2671148 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.7966. Min Range: -3.7966

Max Act: 3.5197. Min Act: -0.1700

Data Index: 4402800 (Open Web Text)

Max Activating Token Index: 1001

Text #19

Max Range: 3.7966. Min Range: -3.7966

Max Act: 3.4423. Min Act: -0.1700

Data Index: 4192180 (Open Web Text)

Max Activating Token Index: 414