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

Dataset: Open Web Text

Neuron 1099 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: 2.1188. Min Range: -2.1188

Max Act: 2.1188. Min Act: -0.1700

Data Index: 7329451 (Open Web Text)

Max Activating Token Index: 48

Text #1

Max Range: 2.1188. Min Range: -2.1188

Max Act: 2.0958. Min Act: -0.1700

Data Index: 7840819 (Open Web Text)

Max Activating Token Index: 13

Text #2

Max Range: 2.1188. Min Range: -2.1188

Max Act: 2.1013. Min Act: -0.1700

Data Index: 2003821 (Open Web Text)

Max Activating Token Index: 33

Text #3

Max Range: 2.1188. Min Range: -2.1188

Max Act: 2.0915. Min Act: -0.1700

Data Index: 4327162 (Open Web Text)

Max Activating Token Index: 14

Text #4

Max Range: 2.1188. Min Range: -2.1188

Max Act: 2.0815. Min Act: -0.1700

Data Index: 2284998 (Open Web Text)

Max Activating Token Index: 29

Text #5

Max Range: 2.1188. Min Range: -2.1188

Max Act: 2.0610. Min Act: -0.1700

Data Index: 3108567 (Open Web Text)

Max Activating Token Index: 56

Text #6

Max Range: 2.1188. Min Range: -2.1188

Max Act: 2.0588. Min Act: -0.1700

Data Index: 836026 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 2.1188. Min Range: -2.1188

Max Act: 2.0742. Min Act: -0.1700

Data Index: 3451439 (Open Web Text)

Max Activating Token Index: 13

Text #8

Max Range: 2.1188. Min Range: -2.1188

Max Act: 2.0664. Min Act: -0.1700

Data Index: 5555907 (Open Web Text)

Max Activating Token Index: 17

Text #9

Max Range: 2.1188. Min Range: -2.1188

Max Act: 2.0598. Min Act: -0.1700

Data Index: 5825102 (Open Web Text)

Max Activating Token Index: 17

Text #10

Max Range: 2.1188. Min Range: -2.1188

Max Act: 2.0474. Min Act: -0.1700

Data Index: 1766957 (Open Web Text)

Max Activating Token Index: 65

Text #11

Max Range: 2.1188. Min Range: -2.1188

Max Act: 2.0506. Min Act: -0.1700

Data Index: 5243449 (Open Web Text)

Max Activating Token Index: 45

Text #12

Max Range: 2.1188. Min Range: -2.1188

Max Act: 2.0486. Min Act: -0.1700

Data Index: 3110908 (Open Web Text)

Max Activating Token Index: 52

Text #13

Max Range: 2.1188. Min Range: -2.1188

Max Act: 2.0548. Min Act: -0.1699

Data Index: 6432404 (Open Web Text)

Max Activating Token Index: 18

Text #14

Max Range: 2.1188. Min Range: -2.1188

Max Act: 2.0563. Min Act: -0.1700

Data Index: 6988894 (Open Web Text)

Max Activating Token Index: 86

Text #15

Max Range: 2.1188. Min Range: -2.1188

Max Act: 2.0514. Min Act: -0.1700

Data Index: 8582544 (Open Web Text)

Max Activating Token Index: 22

Text #16

Max Range: 2.1188. Min Range: -2.1188

Max Act: 2.0452. Min Act: -0.1700

Data Index: 4030582 (Open Web Text)

Max Activating Token Index: 77

Text #17

Max Range: 2.1188. Min Range: -2.1188

Max Act: 2.0358. Min Act: -0.1700

Data Index: 3373539 (Open Web Text)

Max Activating Token Index: 16

Text #18

Max Range: 2.1188. Min Range: -2.1188

Max Act: 2.0298. Min Act: -0.1700

Data Index: 4690341 (Open Web Text)

Max Activating Token Index: 21

Text #19

Max Range: 2.1188. Min Range: -2.1188

Max Act: 2.0364. Min Act: -0.1700

Data Index: 4808783 (Open Web Text)

Max Activating Token Index: 14