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

Dataset: Open Web Text

Neuron 3025 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: 5.0259. Min Range: -5.0259

Max Act: 5.0259. Min Act: -0.1700

Data Index: 2486279 (Open Web Text)

Max Activating Token Index: 21

Text #1

Max Range: 5.0259. Min Range: -5.0259

Max Act: 4.9875. Min Act: -0.1700

Data Index: 8333257 (Open Web Text)

Max Activating Token Index: 33

Text #2

Max Range: 5.0259. Min Range: -5.0259

Max Act: 4.9590. Min Act: -0.1700

Data Index: 6542704 (Open Web Text)

Max Activating Token Index: 10

Text #3

Max Range: 5.0259. Min Range: -5.0259

Max Act: 4.9556. Min Act: -0.1700

Data Index: 6260973 (Open Web Text)

Max Activating Token Index: 33

Text #4

Max Range: 5.0259. Min Range: -5.0259

Max Act: 4.9357. Min Act: -0.1700

Data Index: 8003526 (Open Web Text)

Max Activating Token Index: 30

Text #5

Max Range: 5.0259. Min Range: -5.0259

Max Act: 4.9197. Min Act: -0.1700

Data Index: 4034980 (Open Web Text)

Max Activating Token Index: 51

Text #6

Max Range: 5.0259. Min Range: -5.0259

Max Act: 4.8999. Min Act: -0.1700

Data Index: 3285385 (Open Web Text)

Max Activating Token Index: 79

Text #7

Max Range: 5.0259. Min Range: -5.0259

Max Act: 4.9030. Min Act: -0.1700

Data Index: 1960486 (Open Web Text)

Max Activating Token Index: 191

Text #8

Max Range: 5.0259. Min Range: -5.0259

Max Act: 4.9097. Min Act: -0.1700

Data Index: 808442 (Open Web Text)

Max Activating Token Index: 56

Text #9

Max Range: 5.0259. Min Range: -5.0259

Max Act: 4.9038. Min Act: -0.1700

Data Index: 5268188 (Open Web Text)

Max Activating Token Index: 48

Text #10

Max Range: 5.0259. Min Range: -5.0259

Max Act: 4.8712. Min Act: -0.1700

Data Index: 1733909 (Open Web Text)

Max Activating Token Index: 71

Text #11

Max Range: 5.0259. Min Range: -5.0259

Max Act: 4.8791. Min Act: -0.1700

Data Index: 8714527 (Open Web Text)

Max Activating Token Index: 248

Text #12

Max Range: 5.0259. Min Range: -5.0259

Max Act: 4.8570. Min Act: -0.1700

Data Index: 8596019 (Open Web Text)

Max Activating Token Index: 13

Text #13

Max Range: 5.0259. Min Range: -5.0259

Max Act: 4.8650. Min Act: -0.1700

Data Index: 2382422 (Open Web Text)

Max Activating Token Index: 40

Text #14

Max Range: 5.0259. Min Range: -5.0259

Max Act: 4.8924. Min Act: -0.1700

Data Index: 2046557 (Open Web Text)

Max Activating Token Index: 13

Text #15

Max Range: 5.0259. Min Range: -5.0259

Max Act: 4.8426. Min Act: -0.1700

Data Index: 562975 (Open Web Text)

Max Activating Token Index: 12

Text #16

Max Range: 5.0259. Min Range: -5.0259

Max Act: 4.8544. Min Act: -0.1700

Data Index: 1076165 (Open Web Text)

Max Activating Token Index: 76

Text #17

Max Range: 5.0259. Min Range: -5.0259

Max Act: 4.8294. Min Act: -0.1700

Data Index: 3740327 (Open Web Text)

Max Activating Token Index: 267

Text #18

Max Range: 5.0259. Min Range: -5.0259

Max Act: 4.8286. Min Act: -0.1700

Data Index: 7125080 (Open Web Text)

Max Activating Token Index: 35

Text #19

Max Range: 5.0259. Min Range: -5.0259

Max Act: 4.8414. Min Act: -0.1700

Data Index: 7407869 (Open Web Text)

Max Activating Token Index: 260