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

Dataset: Open Web Text

Neuron 849 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: 3.0498. Min Range: -3.0498

Max Act: 3.0498. Min Act: -0.1700

Data Index: 1551373 (Open Web Text)

Max Activating Token Index: 150

Text #1

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.9679. Min Act: -0.1700

Data Index: 3961972 (Open Web Text)

Max Activating Token Index: 83

Text #2

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.8789. Min Act: -0.1700

Data Index: 98451 (Open Web Text)

Max Activating Token Index: 978

Text #3

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.8738. Min Act: -0.1700

Data Index: 8668570 (Open Web Text)

Max Activating Token Index: 588

Text #4

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.8342. Min Act: -0.1700

Data Index: 399421 (Open Web Text)

Max Activating Token Index: 879

Text #5

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.8664. Min Act: -0.1700

Data Index: 2151397 (Open Web Text)

Max Activating Token Index: 156

Text #6

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.8528. Min Act: -0.1700

Data Index: 7530591 (Open Web Text)

Max Activating Token Index: 531

Text #7

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.8417. Min Act: -0.1700

Data Index: 121994 (Open Web Text)

Max Activating Token Index: 159

Text #8

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.8371. Min Act: -0.1700

Data Index: 5918400 (Open Web Text)

Max Activating Token Index: 342

Text #9

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.8345. Min Act: -0.1700

Data Index: 3280552 (Open Web Text)

Max Activating Token Index: 578

Text #10

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.8401. Min Act: -0.1700

Data Index: 8408486 (Open Web Text)

Max Activating Token Index: 239

Text #11

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.8337. Min Act: -0.1700

Data Index: 3587333 (Open Web Text)

Max Activating Token Index: 173

Text #12

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.8167. Min Act: -0.1700

Data Index: 337388 (Open Web Text)

Max Activating Token Index: 65

Text #13

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.8073. Min Act: -0.1700

Data Index: 4933235 (Open Web Text)

Max Activating Token Index: 726

Text #14

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.7944. Min Act: -0.1700

Data Index: 3608342 (Open Web Text)

Max Activating Token Index: 910

Text #15

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.7996. Min Act: -0.1700

Data Index: 6592754 (Open Web Text)

Max Activating Token Index: 440

Text #16

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.8051. Min Act: -0.1700

Data Index: 614416 (Open Web Text)

Max Activating Token Index: 977

Text #17

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.7681. Min Act: -0.1700

Data Index: 6253285 (Open Web Text)

Max Activating Token Index: 1009

Text #18

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.8131. Min Act: -0.1700

Data Index: 3264848 (Open Web Text)

Max Activating Token Index: 133

Text #19

Max Range: 3.0498. Min Range: -3.0498

Max Act: 2.7701. Min Act: -0.1700

Data Index: 2142756 (Open Web Text)

Max Activating Token Index: 578