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

Dataset: Open Web Text

Neuron 2834 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: 3.3896. Min Range: -3.3896

Max Act: 3.3896. Min Act: -0.1700

Data Index: 6290617 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.3459. Min Act: -0.1700

Data Index: 4266580 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.3462. Min Act: -0.1700

Data Index: 4217940 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.3143. Min Act: -0.1700

Data Index: 5976541 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2647. Min Act: -0.1700

Data Index: 5040730 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2775. Min Act: -0.1700

Data Index: 3301619 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2845. Min Act: -0.1700

Data Index: 8489051 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2909. Min Act: -0.1700

Data Index: 1307719 (Open Web Text)

Max Activating Token Index: 14

Text #8

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2493. Min Act: -0.1700

Data Index: 5033430 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2659. Min Act: -0.1700

Data Index: 1326900 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2463. Min Act: -0.1700

Data Index: 7816161 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2656. Min Act: -0.1700

Data Index: 3398286 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2341. Min Act: -0.1700

Data Index: 1789858 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2547. Min Act: -0.1700

Data Index: 7759087 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2478. Min Act: -0.1700

Data Index: 3088454 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2314. Min Act: -0.1700

Data Index: 6400934 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2581. Min Act: -0.1700

Data Index: 2854515 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2122. Min Act: -0.1700

Data Index: 4207193 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2126. Min Act: -0.1700

Data Index: 4733569 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2066. Min Act: -0.1700

Data Index: 143498 (Open Web Text)

Max Activating Token Index: 6