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

Dataset: Open Web Text

Neuron 2721 in Layer 5

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: 3.6955. Min Range: -3.6955

Max Act: 3.6955. Min Act: -0.1700

Data Index: 4436501 (Open Web Text)

Max Activating Token Index: 499

Text #1

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.5350. Min Act: -0.1700

Data Index: 5532701 (Open Web Text)

Max Activating Token Index: 496

Text #2

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.4612. Min Act: -0.1700

Data Index: 2894411 (Open Web Text)

Max Activating Token Index: 693

Text #3

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.4426. Min Act: -0.1700

Data Index: 7624576 (Open Web Text)

Max Activating Token Index: 217

Text #4

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.4423. Min Act: -0.1700

Data Index: 2343864 (Open Web Text)

Max Activating Token Index: 38

Text #5

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.4076. Min Act: -0.1700

Data Index: 5331227 (Open Web Text)

Max Activating Token Index: 73

Text #6

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.4256. Min Act: -0.1700

Data Index: 1270166 (Open Web Text)

Max Activating Token Index: 88

Text #7

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.4131. Min Act: -0.1700

Data Index: 3551909 (Open Web Text)

Max Activating Token Index: 118

Text #8

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.4197. Min Act: -0.1700

Data Index: 3156090 (Open Web Text)

Max Activating Token Index: 184

Text #9

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.4005. Min Act: -0.1700

Data Index: 198357 (Open Web Text)

Max Activating Token Index: 356

Text #10

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.4023. Min Act: -0.1700

Data Index: 5460641 (Open Web Text)

Max Activating Token Index: 269

Text #11

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.3981. Min Act: -0.1700

Data Index: 1493629 (Open Web Text)

Max Activating Token Index: 680

Text #12

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.3841. Min Act: -0.1700

Data Index: 8174854 (Open Web Text)

Max Activating Token Index: 369

Text #13

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.3526. Min Act: -0.1700

Data Index: 3446303 (Open Web Text)

Max Activating Token Index: 159

Text #14

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.3541. Min Act: -0.1700

Data Index: 4461373 (Open Web Text)

Max Activating Token Index: 64

Text #15

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.3804. Min Act: -0.1700

Data Index: 8616385 (Open Web Text)

Max Activating Token Index: 658

Text #16

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.3484. Min Act: -0.1700

Data Index: 5628980 (Open Web Text)

Max Activating Token Index: 332

Text #17

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.3480. Min Act: -0.1700

Data Index: 6594121 (Open Web Text)

Max Activating Token Index: 615

Text #18

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.3424. Min Act: -0.1700

Data Index: 7254351 (Open Web Text)

Max Activating Token Index: 502

Text #19

Max Range: 3.6955. Min Range: -3.6955

Max Act: 3.3297. Min Act: -0.1700

Data Index: 3365962 (Open Web Text)

Max Activating Token Index: 421