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

Dataset: Open Web Text

Neuron 1965 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: 4.7810. Min Range: -4.7810

Max Act: 4.7810. Min Act: -0.1700

Data Index: 242672 (Open Web Text)

Max Activating Token Index: 455

Text #1

Max Range: 4.7810. Min Range: -4.7810

Max Act: 4.5979. Min Act: -0.1700

Data Index: 1963403 (Open Web Text)

Max Activating Token Index: 451

Text #2

Max Range: 4.7810. Min Range: -4.7810

Max Act: 4.5470. Min Act: -0.1700

Data Index: 3568903 (Open Web Text)

Max Activating Token Index: 908

Text #3

Max Range: 4.7810. Min Range: -4.7810

Max Act: 4.5566. Min Act: -0.1700

Data Index: 7223890 (Open Web Text)

Max Activating Token Index: 17

Text #4

Max Range: 4.7810. Min Range: -4.7810

Max Act: 4.6028. Min Act: -0.1700

Data Index: 1491587 (Open Web Text)

Max Activating Token Index: 47

Text #5

Max Range: 4.7810. Min Range: -4.7810

Max Act: 4.6069. Min Act: -0.1700

Data Index: 5157551 (Open Web Text)

Max Activating Token Index: 869

Text #6

Max Range: 4.7810. Min Range: -4.7810

Max Act: 4.5103. Min Act: -0.1700

Data Index: 3996606 (Open Web Text)

Max Activating Token Index: 948

Text #7

Max Range: 4.7810. Min Range: -4.7810

Max Act: 4.5226. Min Act: -0.1700

Data Index: 5775484 (Open Web Text)

Max Activating Token Index: 521

Text #8

Max Range: 4.7810. Min Range: -4.7810

Max Act: 4.5199. Min Act: -0.1700

Data Index: 4716195 (Open Web Text)

Max Activating Token Index: 302

Text #9

Max Range: 4.7810. Min Range: -4.7810

Max Act: 4.4912. Min Act: -0.1700

Data Index: 8081235 (Open Web Text)

Max Activating Token Index: 841

Text #10

Max Range: 4.7810. Min Range: -4.7810

Max Act: 4.5072. Min Act: -0.1700

Data Index: 2833839 (Open Web Text)

Max Activating Token Index: 566

Text #11

Max Range: 4.7810. Min Range: -4.7810

Max Act: 4.5002. Min Act: -0.1700

Data Index: 5356225 (Open Web Text)

Max Activating Token Index: 375

Text #12

Max Range: 4.7810. Min Range: -4.7810

Max Act: 4.5347. Min Act: -0.1700

Data Index: 2817063 (Open Web Text)

Max Activating Token Index: 450

Text #13

Max Range: 4.7810. Min Range: -4.7810

Max Act: 4.5698. Min Act: -0.1700

Data Index: 4673553 (Open Web Text)

Max Activating Token Index: 782

Text #14

Max Range: 4.7810. Min Range: -4.7810

Max Act: 4.5055. Min Act: -0.1700

Data Index: 7775075 (Open Web Text)

Max Activating Token Index: 512

Text #15

Max Range: 4.7810. Min Range: -4.7810

Max Act: 4.4627. Min Act: -0.1700

Data Index: 6942702 (Open Web Text)

Max Activating Token Index: 450

Text #16

Max Range: 4.7810. Min Range: -4.7810

Max Act: 4.4773. Min Act: -0.1700

Data Index: 4947912 (Open Web Text)

Max Activating Token Index: 997

Text #17

Max Range: 4.7810. Min Range: -4.7810

Max Act: 4.4489. Min Act: -0.1700

Data Index: 1741923 (Open Web Text)

Max Activating Token Index: 555

Text #18

Max Range: 4.7810. Min Range: -4.7810

Max Act: 4.4775. Min Act: -0.1700

Data Index: 2942561 (Open Web Text)

Max Activating Token Index: 887

Text #19

Max Range: 4.7810. Min Range: -4.7810

Max Act: 4.4752. Min Act: -0.1700

Data Index: 6531026 (Open Web Text)

Max Activating Token Index: 755