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

Dataset: Open Web Text

Neuron 1359 in Layer 4

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: 3.4913. Min Range: -3.4913

Max Act: 3.4913. Min Act: -0.1700

Data Index: 7205921 (Open Web Text)

Max Activating Token Index: 95

Text #1

Max Range: 3.4913. Min Range: -3.4913

Max Act: 3.1081. Min Act: -0.1700

Data Index: 1796968 (Open Web Text)

Max Activating Token Index: 997

Text #2

Max Range: 3.4913. Min Range: -3.4913

Max Act: 3.1184. Min Act: -0.1700

Data Index: 7023292 (Open Web Text)

Max Activating Token Index: 218

Text #3

Max Range: 3.4913. Min Range: -3.4913

Max Act: 3.0880. Min Act: -0.1700

Data Index: 204328 (Open Web Text)

Max Activating Token Index: 61

Text #4

Max Range: 3.4913. Min Range: -3.4913

Max Act: 3.0941. Min Act: -0.1700

Data Index: 2049567 (Open Web Text)

Max Activating Token Index: 169

Text #5

Max Range: 3.4913. Min Range: -3.4913

Max Act: 3.0786. Min Act: -0.1700

Data Index: 1495542 (Open Web Text)

Max Activating Token Index: 941

Text #6

Max Range: 3.4913. Min Range: -3.4913

Max Act: 3.0366. Min Act: -0.1700

Data Index: 5392500 (Open Web Text)

Max Activating Token Index: 129

Text #7

Max Range: 3.4913. Min Range: -3.4913

Max Act: 3.0572. Min Act: -0.1700

Data Index: 2245588 (Open Web Text)

Max Activating Token Index: 522

Text #8

Max Range: 3.4913. Min Range: -3.4913

Max Act: 3.0288. Min Act: -0.1700

Data Index: 1601193 (Open Web Text)

Max Activating Token Index: 201

Text #9

Max Range: 3.4913. Min Range: -3.4913

Max Act: 3.0371. Min Act: -0.1700

Data Index: 6519991 (Open Web Text)

Max Activating Token Index: 450

Text #10

Max Range: 3.4913. Min Range: -3.4913

Max Act: 3.0092. Min Act: -0.1700

Data Index: 672427 (Open Web Text)

Max Activating Token Index: 531

Text #11

Max Range: 3.4913. Min Range: -3.4913

Max Act: 3.0286. Min Act: -0.1700

Data Index: 2241366 (Open Web Text)

Max Activating Token Index: 328

Text #12

Max Range: 3.4913. Min Range: -3.4913

Max Act: 3.0168. Min Act: -0.1700

Data Index: 1730878 (Open Web Text)

Max Activating Token Index: 728

Text #13

Max Range: 3.4913. Min Range: -3.4913

Max Act: 3.0003. Min Act: -0.1700

Data Index: 6174967 (Open Web Text)

Max Activating Token Index: 234

Text #14

Max Range: 3.4913. Min Range: -3.4913

Max Act: 2.9783. Min Act: -0.1700

Data Index: 5243707 (Open Web Text)

Max Activating Token Index: 161

Text #15

Max Range: 3.4913. Min Range: -3.4913

Max Act: 2.9717. Min Act: -0.1700

Data Index: 6115264 (Open Web Text)

Max Activating Token Index: 728

Text #16

Max Range: 3.4913. Min Range: -3.4913

Max Act: 2.9611. Min Act: -0.1700

Data Index: 1722421 (Open Web Text)

Max Activating Token Index: 940

Text #17

Max Range: 3.4913. Min Range: -3.4913

Max Act: 2.9453. Min Act: -0.1700

Data Index: 8110432 (Open Web Text)

Max Activating Token Index: 43

Text #18

Max Range: 3.4913. Min Range: -3.4913

Max Act: 2.9318. Min Act: -0.1700

Data Index: 2967557 (Open Web Text)

Max Activating Token Index: 105

Text #19

Max Range: 3.4913. Min Range: -3.4913

Max Act: 2.9309. Min Act: -0.1700

Data Index: 4212824 (Open Web Text)

Max Activating Token Index: 99