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

Dataset: Open Web Text

Neuron 1996 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: 5.1510. Min Range: -5.1510

Max Act: 5.1510. Min Act: -0.1700

Data Index: 2447733 (Open Web Text)

Max Activating Token Index: 14

Text #1

Max Range: 5.1510. Min Range: -5.1510

Max Act: 5.0921. Min Act: -0.1700

Data Index: 3870646 (Open Web Text)

Max Activating Token Index: 14

Text #2

Max Range: 5.1510. Min Range: -5.1510

Max Act: 5.0547. Min Act: -0.1700

Data Index: 7212089 (Open Web Text)

Max Activating Token Index: 23

Text #3

Max Range: 5.1510. Min Range: -5.1510

Max Act: 5.0516. Min Act: -0.1700

Data Index: 7808043 (Open Web Text)

Max Activating Token Index: 40

Text #4

Max Range: 5.1510. Min Range: -5.1510

Max Act: 5.0416. Min Act: -0.1700

Data Index: 7995359 (Open Web Text)

Max Activating Token Index: 21

Text #5

Max Range: 5.1510. Min Range: -5.1510

Max Act: 5.0449. Min Act: -0.1700

Data Index: 5216018 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 5.1510. Min Range: -5.1510

Max Act: 5.0190. Min Act: -0.1700

Data Index: 1602285 (Open Web Text)

Max Activating Token Index: 29

Text #7

Max Range: 5.1510. Min Range: -5.1510

Max Act: 5.0294. Min Act: -0.1700

Data Index: 2888105 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 5.1510. Min Range: -5.1510

Max Act: 5.0362. Min Act: -0.1700

Data Index: 2746089 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 5.1510. Min Range: -5.1510

Max Act: 5.0298. Min Act: -0.1700

Data Index: 5288330 (Open Web Text)

Max Activating Token Index: 15

Text #10

Max Range: 5.1510. Min Range: -5.1510

Max Act: 5.0173. Min Act: -0.1700

Data Index: 4845179 (Open Web Text)

Max Activating Token Index: 33

Text #11

Max Range: 5.1510. Min Range: -5.1510

Max Act: 5.0179. Min Act: -0.1700

Data Index: 3192618 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 5.1510. Min Range: -5.1510

Max Act: 5.0102. Min Act: -0.1700

Data Index: 4529074 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 5.1510. Min Range: -5.1510

Max Act: 5.0075. Min Act: -0.1700

Data Index: 2387952 (Open Web Text)

Max Activating Token Index: 12

Text #14

Max Range: 5.1510. Min Range: -5.1510

Max Act: 5.0293. Min Act: -0.1700

Data Index: 1163779 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 5.1510. Min Range: -5.1510

Max Act: 4.9936. Min Act: -0.1700

Data Index: 2741286 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 5.1510. Min Range: -5.1510

Max Act: 4.9873. Min Act: -0.1700

Data Index: 2115293 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 5.1510. Min Range: -5.1510

Max Act: 4.9921. Min Act: -0.1700

Data Index: 4413500 (Open Web Text)

Max Activating Token Index: 29

Text #18

Max Range: 5.1510. Min Range: -5.1510

Max Act: 4.9969. Min Act: -0.1700

Data Index: 2762294 (Open Web Text)

Max Activating Token Index: 24

Text #19

Max Range: 5.1510. Min Range: -5.1510

Max Act: 4.9885. Min Act: -0.1700

Data Index: 5330794 (Open Web Text)

Max Activating Token Index: 13