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

Dataset: Open Web Text

Neuron 1615 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: 4.1036. Min Range: -4.1036

Max Act: 4.1036. Min Act: -0.1700

Data Index: 4886600 (Open Web Text)

Max Activating Token Index: 937

Text #1

Max Range: 4.1036. Min Range: -4.1036

Max Act: 4.0622. Min Act: -0.1700

Data Index: 7197344 (Open Web Text)

Max Activating Token Index: 836

Text #2

Max Range: 4.1036. Min Range: -4.1036

Max Act: 4.0649. Min Act: -0.1700

Data Index: 294433 (Open Web Text)

Max Activating Token Index: 481

Text #3

Max Range: 4.1036. Min Range: -4.1036

Max Act: 4.0359. Min Act: -0.1700

Data Index: 5191482 (Open Web Text)

Max Activating Token Index: 285

Text #4

Max Range: 4.1036. Min Range: -4.1036

Max Act: 4.0036. Min Act: -0.1700

Data Index: 4040205 (Open Web Text)

Max Activating Token Index: 479

Text #5

Max Range: 4.1036. Min Range: -4.1036

Max Act: 4.0437. Min Act: -0.1700

Data Index: 4695486 (Open Web Text)

Max Activating Token Index: 386

Text #6

Max Range: 4.1036. Min Range: -4.1036

Max Act: 4.0768. Min Act: -0.1700

Data Index: 4231137 (Open Web Text)

Max Activating Token Index: 435

Text #7

Max Range: 4.1036. Min Range: -4.1036

Max Act: 4.0539. Min Act: -0.1700

Data Index: 7736784 (Open Web Text)

Max Activating Token Index: 684

Text #8

Max Range: 4.1036. Min Range: -4.1036

Max Act: 4.0379. Min Act: -0.1700

Data Index: 3352085 (Open Web Text)

Max Activating Token Index: 547

Text #9

Max Range: 4.1036. Min Range: -4.1036

Max Act: 4.0447. Min Act: -0.1700

Data Index: 2920997 (Open Web Text)

Max Activating Token Index: 317

Text #10

Max Range: 4.1036. Min Range: -4.1036

Max Act: 4.0383. Min Act: -0.1700

Data Index: 1440172 (Open Web Text)

Max Activating Token Index: 488

Text #11

Max Range: 4.1036. Min Range: -4.1036

Max Act: 3.9987. Min Act: -0.1700

Data Index: 7677931 (Open Web Text)

Max Activating Token Index: 439

Text #12

Max Range: 4.1036. Min Range: -4.1036

Max Act: 4.0134. Min Act: -0.1700

Data Index: 1430830 (Open Web Text)

Max Activating Token Index: 483

Text #13

Max Range: 4.1036. Min Range: -4.1036

Max Act: 4.0202. Min Act: -0.1700

Data Index: 2145343 (Open Web Text)

Max Activating Token Index: 28

Text #14

Max Range: 4.1036. Min Range: -4.1036

Max Act: 4.0156. Min Act: -0.1700

Data Index: 7601673 (Open Web Text)

Max Activating Token Index: 930

Text #15

Max Range: 4.1036. Min Range: -4.1036

Max Act: 4.0499. Min Act: -0.1700

Data Index: 902505 (Open Web Text)

Max Activating Token Index: 1012

Text #16

Max Range: 4.1036. Min Range: -4.1036

Max Act: 3.9860. Min Act: -0.1700

Data Index: 7256448 (Open Web Text)

Max Activating Token Index: 949

Text #17

Max Range: 4.1036. Min Range: -4.1036

Max Act: 3.9916. Min Act: -0.1700

Data Index: 4670684 (Open Web Text)

Max Activating Token Index: 962

Text #18

Max Range: 4.1036. Min Range: -4.1036

Max Act: 3.9890. Min Act: -0.1700

Data Index: 686931 (Open Web Text)

Max Activating Token Index: 809

Text #19

Max Range: 4.1036. Min Range: -4.1036

Max Act: 3.9960. Min Act: -0.1700

Data Index: 277618 (Open Web Text)

Max Activating Token Index: 543