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

Dataset: Open Web Text

Neuron 205 in Layer 3

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: 3.5795. Min Range: -3.5795

Max Act: 3.5795. Min Act: -0.1700

Data Index: 6615773 (Open Web Text)

Max Activating Token Index: 827

Text #1

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.5196. Min Act: -0.1700

Data Index: 2342992 (Open Web Text)

Max Activating Token Index: 798

Text #2

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.4798. Min Act: -0.1700

Data Index: 2540169 (Open Web Text)

Max Activating Token Index: 186

Text #3

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.4627. Min Act: -0.1700

Data Index: 3781578 (Open Web Text)

Max Activating Token Index: 877

Text #4

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.3900. Min Act: -0.1700

Data Index: 2366645 (Open Web Text)

Max Activating Token Index: 80

Text #5

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.3888. Min Act: -0.1700

Data Index: 2324168 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.3932. Min Act: -0.1700

Data Index: 1549092 (Open Web Text)

Max Activating Token Index: 362

Text #7

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.3677. Min Act: -0.1700

Data Index: 2082925 (Open Web Text)

Max Activating Token Index: 189

Text #8

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.3566. Min Act: -0.1700

Data Index: 3524275 (Open Web Text)

Max Activating Token Index: 884

Text #9

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.3943. Min Act: -0.1700

Data Index: 7269164 (Open Web Text)

Max Activating Token Index: 44

Text #10

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.3286. Min Act: -0.1700

Data Index: 6185996 (Open Web Text)

Max Activating Token Index: 474

Text #11

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.3536. Min Act: -0.1700

Data Index: 351057 (Open Web Text)

Max Activating Token Index: 670

Text #12

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.3245. Min Act: -0.1700

Data Index: 4774438 (Open Web Text)

Max Activating Token Index: 614

Text #13

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.3445. Min Act: -0.1700

Data Index: 5695954 (Open Web Text)

Max Activating Token Index: 679

Text #14

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.3326. Min Act: -0.1700

Data Index: 1986147 (Open Web Text)

Max Activating Token Index: 755

Text #15

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.3172. Min Act: -0.1700

Data Index: 7938770 (Open Web Text)

Max Activating Token Index: 686

Text #16

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.3067. Min Act: -0.1700

Data Index: 7490334 (Open Web Text)

Max Activating Token Index: 698

Text #17

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.3234. Min Act: -0.1700

Data Index: 1611857 (Open Web Text)

Max Activating Token Index: 1004

Text #18

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.2986. Min Act: -0.1700

Data Index: 6960827 (Open Web Text)

Max Activating Token Index: 233

Text #19

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.2669. Min Act: -0.1700

Data Index: 3165440 (Open Web Text)

Max Activating Token Index: 515