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

Dataset: Open Web Text

Neuron 1931 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: 3.4266. Min Range: -3.4266

Max Act: 3.4266. Min Act: -0.1700

Data Index: 8619688 (Open Web Text)

Max Activating Token Index: 793

Text #1

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.3676. Min Act: -0.1700

Data Index: 7384305 (Open Web Text)

Max Activating Token Index: 524

Text #2

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.3717. Min Act: -0.1700

Data Index: 8196509 (Open Web Text)

Max Activating Token Index: 24

Text #3

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.3656. Min Act: -0.1700

Data Index: 3395404 (Open Web Text)

Max Activating Token Index: 113

Text #4

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.3339. Min Act: -0.1700

Data Index: 8396433 (Open Web Text)

Max Activating Token Index: 167

Text #5

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.3302. Min Act: -0.1700

Data Index: 7637878 (Open Web Text)

Max Activating Token Index: 148

Text #6

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.3120. Min Act: -0.1700

Data Index: 5999783 (Open Web Text)

Max Activating Token Index: 122

Text #7

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.3121. Min Act: -0.1700

Data Index: 4226864 (Open Web Text)

Max Activating Token Index: 879

Text #8

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.2963. Min Act: -0.1700

Data Index: 7752948 (Open Web Text)

Max Activating Token Index: 91

Text #9

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.2830. Min Act: -0.1700

Data Index: 5308547 (Open Web Text)

Max Activating Token Index: 249

Text #10

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.2917. Min Act: -0.1700

Data Index: 3903585 (Open Web Text)

Max Activating Token Index: 79

Text #11

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.2900. Min Act: -0.1700

Data Index: 1156025 (Open Web Text)

Max Activating Token Index: 299

Text #12

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.3136. Min Act: -0.1700

Data Index: 5606245 (Open Web Text)

Max Activating Token Index: 111

Text #13

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.2807. Min Act: -0.1700

Data Index: 6110014 (Open Web Text)

Max Activating Token Index: 58

Text #14

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.2750. Min Act: -0.1700

Data Index: 8557431 (Open Web Text)

Max Activating Token Index: 144

Text #15

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.2781. Min Act: -0.1700

Data Index: 1156996 (Open Web Text)

Max Activating Token Index: 439

Text #16

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.2820. Min Act: -0.1700

Data Index: 3174024 (Open Web Text)

Max Activating Token Index: 60

Text #17

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.2638. Min Act: -0.1700

Data Index: 5529219 (Open Web Text)

Max Activating Token Index: 181

Text #18

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.2682. Min Act: -0.1700

Data Index: 2318166 (Open Web Text)

Max Activating Token Index: 148

Text #19

Max Range: 3.4266. Min Range: -3.4266

Max Act: 3.2551. Min Act: -0.1700

Data Index: 2273455 (Open Web Text)

Max Activating Token Index: 857