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

Dataset: Open Web Text

Neuron 402 in Layer 1

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: 1.7767. Min Range: -1.7767

Max Act: 1.7767. Min Act: -0.1700

Data Index: 3449994 (Open Web Text)

Max Activating Token Index: 386

Text #1

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.6949. Min Act: -0.1694

Data Index: 7957724 (Open Web Text)

Max Activating Token Index: 80

Text #2

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.6712. Min Act: -0.1699

Data Index: 7134584 (Open Web Text)

Max Activating Token Index: 364

Text #3

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.6684. Min Act: -0.1666

Data Index: 7371016 (Open Web Text)

Max Activating Token Index: 602

Text #4

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.6650. Min Act: -0.1700

Data Index: 8270981 (Open Web Text)

Max Activating Token Index: 492

Text #5

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.6674. Min Act: -0.1700

Data Index: 3129241 (Open Web Text)

Max Activating Token Index: 508

Text #6

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.6608. Min Act: -0.1700

Data Index: 703804 (Open Web Text)

Max Activating Token Index: 223

Text #7

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.6707. Min Act: -0.1700

Data Index: 5079242 (Open Web Text)

Max Activating Token Index: 526

Text #8

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.6554. Min Act: -0.1700

Data Index: 3449993 (Open Web Text)

Max Activating Token Index: 482

Text #9

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.6628. Min Act: -0.1700

Data Index: 3497721 (Open Web Text)

Max Activating Token Index: 503

Text #10

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.6489. Min Act: -0.1699

Data Index: 7957723 (Open Web Text)

Max Activating Token Index: 948

Text #11

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.6260. Min Act: -0.1697

Data Index: 6512324 (Open Web Text)

Max Activating Token Index: 784

Text #12

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.6334. Min Act: -0.1700

Data Index: 5068800 (Open Web Text)

Max Activating Token Index: 39

Text #13

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.6293. Min Act: -0.1700

Data Index: 5335167 (Open Web Text)

Max Activating Token Index: 453

Text #14

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.6249. Min Act: -0.1686

Data Index: 378068 (Open Web Text)

Max Activating Token Index: 429

Text #15

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.6136. Min Act: -0.1700

Data Index: 993424 (Open Web Text)

Max Activating Token Index: 948

Text #16

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.6173. Min Act: -0.1697

Data Index: 440215 (Open Web Text)

Max Activating Token Index: 178

Text #17

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.6103. Min Act: -0.1700

Data Index: 3590092 (Open Web Text)

Max Activating Token Index: 34

Text #18

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.6153. Min Act: -0.1700

Data Index: 4037066 (Open Web Text)

Max Activating Token Index: 655

Text #19

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.6067. Min Act: -0.1700

Data Index: 4558440 (Open Web Text)

Max Activating Token Index: 220