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

Dataset: Open Web Text

Neuron 600 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: 3.8464. Min Range: -3.8464

Max Act: 3.8204. Min Act: -0.1700

Data Index: 8813287 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.8464. Min Act: -0.1700

Data Index: 5277044 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.8248. Min Act: -0.1700

Data Index: 2611557 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.8357. Min Act: -0.1700

Data Index: 7763717 (Open Web Text)

Max Activating Token Index: 742

Text #4

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.8179. Min Act: -0.1700

Data Index: 1288023 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.7889. Min Act: -0.1700

Data Index: 5482608 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.7910. Min Act: -0.1700

Data Index: 420022 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.7896. Min Act: -0.1700

Data Index: 7875026 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.8033. Min Act: -0.1700

Data Index: 7342323 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.7903. Min Act: -0.1700

Data Index: 3766508 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.8001. Min Act: -0.1700

Data Index: 6970974 (Open Web Text)

Max Activating Token Index: 160

Text #11

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.8031. Min Act: -0.1700

Data Index: 2624512 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.7873. Min Act: -0.1700

Data Index: 6442039 (Open Web Text)

Max Activating Token Index: 12

Text #13

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.7676. Min Act: -0.1700

Data Index: 7203379 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.7843. Min Act: -0.1700

Data Index: 265707 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.7663. Min Act: -0.1700

Data Index: 7772288 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.7637. Min Act: -0.1700

Data Index: 1448197 (Open Web Text)

Max Activating Token Index: 175

Text #17

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.7634. Min Act: -0.1700

Data Index: 2436066 (Open Web Text)

Max Activating Token Index: 716

Text #18

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.7631. Min Act: -0.1700

Data Index: 8236830 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.7711. Min Act: -0.1700

Data Index: 6340921 (Open Web Text)

Max Activating Token Index: 28