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

Dataset: Open Web Text

Neuron 975 in Layer 5

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: 4.8582. Min Range: -4.8582

Max Act: 4.8462. Min Act: -0.1700

Data Index: 2239335 (Open Web Text)

Max Activating Token Index: 426

Text #1

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.8582. Min Act: -0.1700

Data Index: 8187645 (Open Web Text)

Max Activating Token Index: 916

Text #2

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.8438. Min Act: -0.1700

Data Index: 8515217 (Open Web Text)

Max Activating Token Index: 1005

Text #3

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.8046. Min Act: -0.1700

Data Index: 8570983 (Open Web Text)

Max Activating Token Index: 63

Text #4

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.7475. Min Act: -0.1700

Data Index: 5104677 (Open Web Text)

Max Activating Token Index: 298

Text #5

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.7376. Min Act: -0.1700

Data Index: 57416 (Open Web Text)

Max Activating Token Index: 500

Text #6

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.7869. Min Act: -0.1700

Data Index: 1400162 (Open Web Text)

Max Activating Token Index: 211

Text #7

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.7745. Min Act: -0.1700

Data Index: 4528020 (Open Web Text)

Max Activating Token Index: 821

Text #8

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.7043. Min Act: -0.1700

Data Index: 8228180 (Open Web Text)

Max Activating Token Index: 541

Text #9

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.6523. Min Act: -0.1700

Data Index: 3065888 (Open Web Text)

Max Activating Token Index: 312

Text #10

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.6269. Min Act: -0.1700

Data Index: 8581004 (Open Web Text)

Max Activating Token Index: 189

Text #11

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.6208. Min Act: -0.1700

Data Index: 8779106 (Open Web Text)

Max Activating Token Index: 153

Text #12

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.6424. Min Act: -0.1700

Data Index: 997304 (Open Web Text)

Max Activating Token Index: 280

Text #13

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.6534. Min Act: -0.1700

Data Index: 1048218 (Open Web Text)

Max Activating Token Index: 290

Text #14

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.6793. Min Act: -0.1700

Data Index: 3417002 (Open Web Text)

Max Activating Token Index: 233

Text #15

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.5979. Min Act: -0.1700

Data Index: 1680237 (Open Web Text)

Max Activating Token Index: 793

Text #16

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.6549. Min Act: -0.1700

Data Index: 951450 (Open Web Text)

Max Activating Token Index: 866

Text #17

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.6004. Min Act: -0.1700

Data Index: 5322027 (Open Web Text)

Max Activating Token Index: 356

Text #18

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.5919. Min Act: -0.1700

Data Index: 3109177 (Open Web Text)

Max Activating Token Index: 920

Text #19

Max Range: 4.8582. Min Range: -4.8582

Max Act: 4.5844. Min Act: -0.1700

Data Index: 3303790 (Open Web Text)

Max Activating Token Index: 438