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

Dataset: Open Web Text

Neuron 1516 in Layer 0

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: 4.1374. Min Range: -4.1374

Max Act: 4.1374. Min Act: -0.1700

Data Index: 6345732 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.1374. Min Range: -4.1374

Max Act: 4.0814. Min Act: -0.1700

Data Index: 6490036 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.1374. Min Range: -4.1374

Max Act: 4.0387. Min Act: -0.1700

Data Index: 7601205 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.1374. Min Range: -4.1374

Max Act: 4.0121. Min Act: -0.1700

Data Index: 7675245 (Open Web Text)

Max Activating Token Index: 14

Text #4

Max Range: 4.1374. Min Range: -4.1374

Max Act: 3.9948. Min Act: -0.1700

Data Index: 7154288 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.1374. Min Range: -4.1374

Max Act: 3.9811. Min Act: -0.1700

Data Index: 6554652 (Open Web Text)

Max Activating Token Index: 24

Text #6

Max Range: 4.1374. Min Range: -4.1374

Max Act: 3.9724. Min Act: -0.1700

Data Index: 5016914 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.1374. Min Range: -4.1374

Max Act: 3.9309. Min Act: -0.1700

Data Index: 3518142 (Open Web Text)

Max Activating Token Index: 36

Text #8

Max Range: 4.1374. Min Range: -4.1374

Max Act: 3.9389. Min Act: -0.1700

Data Index: 8024194 (Open Web Text)

Max Activating Token Index: 18

Text #9

Max Range: 4.1374. Min Range: -4.1374

Max Act: 3.9601. Min Act: -0.1700

Data Index: 7255482 (Open Web Text)

Max Activating Token Index: 1007

Text #10

Max Range: 4.1374. Min Range: -4.1374

Max Act: 3.9487. Min Act: -0.1700

Data Index: 2342628 (Open Web Text)

Max Activating Token Index: 113

Text #11

Max Range: 4.1374. Min Range: -4.1374

Max Act: 3.9408. Min Act: -0.1700

Data Index: 1945278 (Open Web Text)

Max Activating Token Index: 907

Text #12

Max Range: 4.1374. Min Range: -4.1374

Max Act: 3.9482. Min Act: -0.1700

Data Index: 390709 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 4.1374. Min Range: -4.1374

Max Act: 3.9549. Min Act: -0.1700

Data Index: 3232192 (Open Web Text)

Max Activating Token Index: 79

Text #14

Max Range: 4.1374. Min Range: -4.1374

Max Act: 3.9154. Min Act: -0.1700

Data Index: 1278655 (Open Web Text)

Max Activating Token Index: 14

Text #15

Max Range: 4.1374. Min Range: -4.1374

Max Act: 3.9015. Min Act: -0.1700

Data Index: 1656175 (Open Web Text)

Max Activating Token Index: 17

Text #16

Max Range: 4.1374. Min Range: -4.1374

Max Act: 3.9004. Min Act: -0.1700

Data Index: 3132050 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 4.1374. Min Range: -4.1374

Max Act: 3.8853. Min Act: -0.1700

Data Index: 7185263 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 4.1374. Min Range: -4.1374

Max Act: 3.8692. Min Act: -0.1700

Data Index: 5063341 (Open Web Text)

Max Activating Token Index: 690

Text #19

Max Range: 4.1374. Min Range: -4.1374

Max Act: 3.8879. Min Act: -0.1700

Data Index: 325348 (Open Web Text)

Max Activating Token Index: 810