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

Dataset: Open Web Text

Neuron 656 in Layer 2

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: 5.0961. Min Range: -5.0961

Max Act: 5.0961. Min Act: -0.1700

Data Index: 5454584 (Open Web Text)

Max Activating Token Index: 32

Text #1

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.9658. Min Act: -0.1700

Data Index: 3120102 (Open Web Text)

Max Activating Token Index: 224

Text #2

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.9569. Min Act: -0.1700

Data Index: 7742575 (Open Web Text)

Max Activating Token Index: 59

Text #3

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.9565. Min Act: -0.1700

Data Index: 7534596 (Open Web Text)

Max Activating Token Index: 1009

Text #4

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.9016. Min Act: -0.1700

Data Index: 4248062 (Open Web Text)

Max Activating Token Index: 275

Text #5

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.8990. Min Act: -0.1700

Data Index: 8503401 (Open Web Text)

Max Activating Token Index: 619

Text #6

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.9150. Min Act: -0.1700

Data Index: 4984291 (Open Web Text)

Max Activating Token Index: 59

Text #7

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.8851. Min Act: -0.1700

Data Index: 4504163 (Open Web Text)

Max Activating Token Index: 739

Text #8

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.8597. Min Act: -0.1700

Data Index: 7754683 (Open Web Text)

Max Activating Token Index: 348

Text #9

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.8067. Min Act: -0.1700

Data Index: 1610875 (Open Web Text)

Max Activating Token Index: 645

Text #10

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.8679. Min Act: -0.1700

Data Index: 968727 (Open Web Text)

Max Activating Token Index: 612

Text #11

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.8813. Min Act: -0.1700

Data Index: 1201113 (Open Web Text)

Max Activating Token Index: 21

Text #12

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.8309. Min Act: -0.1700

Data Index: 8450096 (Open Web Text)

Max Activating Token Index: 686

Text #13

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.8275. Min Act: -0.1700

Data Index: 8821619 (Open Web Text)

Max Activating Token Index: 668

Text #14

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.8116. Min Act: -0.1700

Data Index: 5626132 (Open Web Text)

Max Activating Token Index: 970

Text #15

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.8039. Min Act: -0.1700

Data Index: 4840162 (Open Web Text)

Max Activating Token Index: 689

Text #16

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.7746. Min Act: -0.1699

Data Index: 5626128 (Open Web Text)

Max Activating Token Index: 701

Text #17

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.7788. Min Act: -0.1700

Data Index: 6733411 (Open Web Text)

Max Activating Token Index: 721

Text #18

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.8337. Min Act: -0.1700

Data Index: 4878388 (Open Web Text)

Max Activating Token Index: 806

Text #19

Max Range: 5.0961. Min Range: -5.0961

Max Act: 4.7637. Min Act: -0.1700

Data Index: 2278685 (Open Web Text)

Max Activating Token Index: 949