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

Dataset: Open Web Text

Neuron 281 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: 3.9960. Min Range: -3.9960

Max Act: 3.9960. Min Act: -0.1700

Data Index: 97690 (Open Web Text)

Max Activating Token Index: 70

Text #1

Max Range: 3.9960. Min Range: -3.9960

Max Act: 3.9759. Min Act: -0.1700

Data Index: 1133345 (Open Web Text)

Max Activating Token Index: 187

Text #2

Max Range: 3.9960. Min Range: -3.9960

Max Act: 3.9794. Min Act: -0.1700

Data Index: 5604053 (Open Web Text)

Max Activating Token Index: 82

Text #3

Max Range: 3.9960. Min Range: -3.9960

Max Act: 3.9485. Min Act: -0.1700

Data Index: 3659197 (Open Web Text)

Max Activating Token Index: 104

Text #4

Max Range: 3.9960. Min Range: -3.9960

Max Act: 3.9245. Min Act: -0.1700

Data Index: 3406972 (Open Web Text)

Max Activating Token Index: 32

Text #5

Max Range: 3.9960. Min Range: -3.9960

Max Act: 3.9401. Min Act: -0.1700

Data Index: 2468404 (Open Web Text)

Max Activating Token Index: 74

Text #6

Max Range: 3.9960. Min Range: -3.9960

Max Act: 3.9085. Min Act: -0.1700

Data Index: 3998456 (Open Web Text)

Max Activating Token Index: 426

Text #7

Max Range: 3.9960. Min Range: -3.9960

Max Act: 3.8879. Min Act: -0.1700

Data Index: 1654845 (Open Web Text)

Max Activating Token Index: 191

Text #8

Max Range: 3.9960. Min Range: -3.9960

Max Act: 3.8895. Min Act: -0.1700

Data Index: 1771965 (Open Web Text)

Max Activating Token Index: 696

Text #9

Max Range: 3.9960. Min Range: -3.9960

Max Act: 3.8759. Min Act: -0.1700

Data Index: 6033048 (Open Web Text)

Max Activating Token Index: 265

Text #10

Max Range: 3.9960. Min Range: -3.9960

Max Act: 3.8955. Min Act: -0.1700

Data Index: 5971984 (Open Web Text)

Max Activating Token Index: 354

Text #11

Max Range: 3.9960. Min Range: -3.9960

Max Act: 3.8892. Min Act: -0.1700

Data Index: 5776979 (Open Web Text)

Max Activating Token Index: 49

Text #12

Max Range: 3.9960. Min Range: -3.9960

Max Act: 3.8859. Min Act: -0.1700

Data Index: 3119516 (Open Web Text)

Max Activating Token Index: 156

Text #13

Max Range: 3.9960. Min Range: -3.9960

Max Act: 3.8975. Min Act: -0.1700

Data Index: 6465594 (Open Web Text)

Max Activating Token Index: 420

Text #14

Max Range: 3.9960. Min Range: -3.9960

Max Act: 3.8983. Min Act: -0.1700

Data Index: 4308014 (Open Web Text)

Max Activating Token Index: 448

Text #15

Max Range: 3.9960. Min Range: -3.9960

Max Act: 3.8565. Min Act: -0.1700

Data Index: 5611889 (Open Web Text)

Max Activating Token Index: 558

Text #16

Max Range: 3.9960. Min Range: -3.9960

Max Act: 3.8578. Min Act: -0.1700

Data Index: 4406545 (Open Web Text)

Max Activating Token Index: 509

Text #17

Max Range: 3.9960. Min Range: -3.9960

Max Act: 3.8711. Min Act: -0.1700

Data Index: 3239932 (Open Web Text)

Max Activating Token Index: 1001

Text #18

Max Range: 3.9960. Min Range: -3.9960

Max Act: 3.8526. Min Act: -0.1700

Data Index: 2269976 (Open Web Text)

Max Activating Token Index: 16

Text #19

Max Range: 3.9960. Min Range: -3.9960

Max Act: 3.8389. Min Act: -0.1700

Data Index: 6249822 (Open Web Text)

Max Activating Token Index: 33