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

Dataset: Open Web Text

Neuron 318 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: 2.1477. Min Range: -2.1477

Max Act: 2.1477. Min Act: -0.1700

Data Index: 8031564 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 2.1477. Min Range: -2.1477

Max Act: 2.1301. Min Act: -0.1700

Data Index: 2920733 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 2.1477. Min Range: -2.1477

Max Act: 2.1407. Min Act: -0.1697

Data Index: 104902 (Open Web Text)

Max Activating Token Index: 821

Text #3

Max Range: 2.1477. Min Range: -2.1477

Max Act: 2.1388. Min Act: -0.1700

Data Index: 2531259 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 2.1477. Min Range: -2.1477

Max Act: 2.1214. Min Act: -0.1700

Data Index: 3833262 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 2.1477. Min Range: -2.1477

Max Act: 2.1169. Min Act: -0.1700

Data Index: 7624667 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 2.1477. Min Range: -2.1477

Max Act: 2.1250. Min Act: -0.1697

Data Index: 2430806 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 2.1477. Min Range: -2.1477

Max Act: 2.0953. Min Act: -0.1697

Data Index: 910174 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 2.1477. Min Range: -2.1477

Max Act: 2.0967. Min Act: -0.1699

Data Index: 595531 (Open Web Text)

Max Activating Token Index: 78

Text #9

Max Range: 2.1477. Min Range: -2.1477

Max Act: 2.0959. Min Act: -0.1698

Data Index: 1213109 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 2.1477. Min Range: -2.1477

Max Act: 2.0947. Min Act: -0.1700

Data Index: 7712996 (Open Web Text)

Max Activating Token Index: 84

Text #11

Max Range: 2.1477. Min Range: -2.1477

Max Act: 2.1015. Min Act: -0.1700

Data Index: 7848401 (Open Web Text)

Max Activating Token Index: 915

Text #12

Max Range: 2.1477. Min Range: -2.1477

Max Act: 2.1035. Min Act: -0.1700

Data Index: 4618359 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 2.1477. Min Range: -2.1477

Max Act: 2.0869. Min Act: -0.1699

Data Index: 2049612 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 2.1477. Min Range: -2.1477

Max Act: 2.0869. Min Act: -0.1700

Data Index: 2481263 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 2.1477. Min Range: -2.1477

Max Act: 2.0829. Min Act: -0.1700

Data Index: 7303112 (Open Web Text)

Max Activating Token Index: 14

Text #16

Max Range: 2.1477. Min Range: -2.1477

Max Act: 2.0851. Min Act: -0.1700

Data Index: 6580585 (Open Web Text)

Max Activating Token Index: 14

Text #17

Max Range: 2.1477. Min Range: -2.1477

Max Act: 2.0821. Min Act: -0.1700

Data Index: 3993465 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 2.1477. Min Range: -2.1477

Max Act: 2.0869. Min Act: -0.1700

Data Index: 1150480 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 2.1477. Min Range: -2.1477

Max Act: 2.0865. Min Act: -0.1700

Data Index: 4439609 (Open Web Text)

Max Activating Token Index: 16