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

Dataset: Open Web Text

Neuron 857 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: 4.5551. Min Range: -4.5551

Max Act: 4.5551. Min Act: -0.1700

Data Index: 2928151 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.5551. Min Range: -4.5551

Max Act: 4.5374. Min Act: -0.1700

Data Index: 8644053 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 4.5551. Min Range: -4.5551

Max Act: 4.2856. Min Act: -0.1700

Data Index: 5536174 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 4.5551. Min Range: -4.5551

Max Act: 4.1773. Min Act: -0.1700

Data Index: 3437225 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 4.5551. Min Range: -4.5551

Max Act: 4.1545. Min Act: -0.1700

Data Index: 3696495 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 4.5551. Min Range: -4.5551

Max Act: 4.1450. Min Act: -0.1700

Data Index: 5018009 (Open Web Text)

Max Activating Token Index: 16

Text #6

Max Range: 4.5551. Min Range: -4.5551

Max Act: 4.1264. Min Act: -0.1700

Data Index: 5254936 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.5551. Min Range: -4.5551

Max Act: 4.0930. Min Act: -0.1700

Data Index: 3014742 (Open Web Text)

Max Activating Token Index: 418

Text #8

Max Range: 4.5551. Min Range: -4.5551

Max Act: 4.0567. Min Act: -0.1700

Data Index: 3433864 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.5551. Min Range: -4.5551

Max Act: 4.0443. Min Act: -0.1700

Data Index: 1336159 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 4.5551. Min Range: -4.5551

Max Act: 4.0386. Min Act: -0.1700

Data Index: 3493163 (Open Web Text)

Max Activating Token Index: 55

Text #11

Max Range: 4.5551. Min Range: -4.5551

Max Act: 4.0416. Min Act: -0.1700

Data Index: 7494674 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 4.5551. Min Range: -4.5551

Max Act: 4.0352. Min Act: -0.1700

Data Index: 1533070 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.5551. Min Range: -4.5551

Max Act: 4.0420. Min Act: -0.1700

Data Index: 6211179 (Open Web Text)

Max Activating Token Index: 12

Text #14

Max Range: 4.5551. Min Range: -4.5551

Max Act: 4.0381. Min Act: -0.1700

Data Index: 5573461 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 4.5551. Min Range: -4.5551

Max Act: 3.9833. Min Act: -0.1700

Data Index: 3060157 (Open Web Text)

Max Activating Token Index: 41

Text #16

Max Range: 4.5551. Min Range: -4.5551

Max Act: 3.9947. Min Act: -0.1700

Data Index: 3147875 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.5551. Min Range: -4.5551

Max Act: 3.9949. Min Act: -0.1700

Data Index: 3287086 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 4.5551. Min Range: -4.5551

Max Act: 4.0079. Min Act: -0.1700

Data Index: 5360513 (Open Web Text)

Max Activating Token Index: 16

Text #19

Max Range: 4.5551. Min Range: -4.5551

Max Act: 3.9902. Min Act: -0.1700

Data Index: 1433053 (Open Web Text)

Max Activating Token Index: 28