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

Dataset: Open Web Text

Neuron 1775 in Layer 6

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: 4.2046. Min Range: -4.2046

Max Act: 4.2046. Min Act: -0.1700

Data Index: 1305189 (Open Web Text)

Max Activating Token Index: 87

Text #1

Max Range: 4.2046. Min Range: -4.2046

Max Act: 4.0114. Min Act: -0.1700

Data Index: 552990 (Open Web Text)

Max Activating Token Index: 511

Text #2

Max Range: 4.2046. Min Range: -4.2046

Max Act: 4.0230. Min Act: -0.1700

Data Index: 4779361 (Open Web Text)

Max Activating Token Index: 324

Text #3

Max Range: 4.2046. Min Range: -4.2046

Max Act: 4.0317. Min Act: -0.1700

Data Index: 1054192 (Open Web Text)

Max Activating Token Index: 726

Text #4

Max Range: 4.2046. Min Range: -4.2046

Max Act: 3.9761. Min Act: -0.1700

Data Index: 5494709 (Open Web Text)

Max Activating Token Index: 1015

Text #5

Max Range: 4.2046. Min Range: -4.2046

Max Act: 3.9717. Min Act: -0.1700

Data Index: 5870816 (Open Web Text)

Max Activating Token Index: 389

Text #6

Max Range: 4.2046. Min Range: -4.2046

Max Act: 3.9903. Min Act: -0.1700

Data Index: 3427415 (Open Web Text)

Max Activating Token Index: 87

Text #7

Max Range: 4.2046. Min Range: -4.2046

Max Act: 3.9299. Min Act: -0.1700

Data Index: 2421414 (Open Web Text)

Max Activating Token Index: 426

Text #8

Max Range: 4.2046. Min Range: -4.2046

Max Act: 3.9414. Min Act: -0.1700

Data Index: 5420797 (Open Web Text)

Max Activating Token Index: 591

Text #9

Max Range: 4.2046. Min Range: -4.2046

Max Act: 3.9257. Min Act: -0.1700

Data Index: 8453287 (Open Web Text)

Max Activating Token Index: 931

Text #10

Max Range: 4.2046. Min Range: -4.2046

Max Act: 3.9372. Min Act: -0.1700

Data Index: 832100 (Open Web Text)

Max Activating Token Index: 88

Text #11

Max Range: 4.2046. Min Range: -4.2046

Max Act: 3.9042. Min Act: -0.1700

Data Index: 5247861 (Open Web Text)

Max Activating Token Index: 403

Text #12

Max Range: 4.2046. Min Range: -4.2046

Max Act: 3.9553. Min Act: -0.1700

Data Index: 5055261 (Open Web Text)

Max Activating Token Index: 1013

Text #13

Max Range: 4.2046. Min Range: -4.2046

Max Act: 3.9226. Min Act: -0.1700

Data Index: 7666952 (Open Web Text)

Max Activating Token Index: 254

Text #14

Max Range: 4.2046. Min Range: -4.2046

Max Act: 3.9141. Min Act: -0.1700

Data Index: 2762804 (Open Web Text)

Max Activating Token Index: 821

Text #15

Max Range: 4.2046. Min Range: -4.2046

Max Act: 3.8741. Min Act: -0.1700

Data Index: 2459491 (Open Web Text)

Max Activating Token Index: 901

Text #16

Max Range: 4.2046. Min Range: -4.2046

Max Act: 3.8719. Min Act: -0.1700

Data Index: 6708254 (Open Web Text)

Max Activating Token Index: 62

Text #17

Max Range: 4.2046. Min Range: -4.2046

Max Act: 3.8680. Min Act: -0.1700

Data Index: 6739539 (Open Web Text)

Max Activating Token Index: 1009

Text #18

Max Range: 4.2046. Min Range: -4.2046

Max Act: 3.8690. Min Act: -0.1700

Data Index: 7344566 (Open Web Text)

Max Activating Token Index: 92

Text #19

Max Range: 4.2046. Min Range: -4.2046

Max Act: 3.8715. Min Act: -0.1700

Data Index: 7961979 (Open Web Text)

Max Activating Token Index: 524