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

Dataset: Open Web Text

Neuron 1881 in Layer 1

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: 1.6401. Min Range: -1.6401

Max Act: 1.6401. Min Act: -0.1700

Data Index: 8189921 (Open Web Text)

Max Activating Token Index: 584

Text #1

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.5259. Min Act: -0.1700

Data Index: 4688702 (Open Web Text)

Max Activating Token Index: 966

Text #2

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.5125. Min Act: -0.1700

Data Index: 2156133 (Open Web Text)

Max Activating Token Index: 12

Text #3

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.5203. Min Act: -0.1700

Data Index: 293644 (Open Web Text)

Max Activating Token Index: 651

Text #4

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.5024. Min Act: -0.1700

Data Index: 5111527 (Open Web Text)

Max Activating Token Index: 1010

Text #5

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.5088. Min Act: -0.1693

Data Index: 3189126 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.5093. Min Act: -0.1700

Data Index: 4823568 (Open Web Text)

Max Activating Token Index: 389

Text #7

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.5077. Min Act: -0.1700

Data Index: 6199280 (Open Web Text)

Max Activating Token Index: 680

Text #8

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.5018. Min Act: -0.1700

Data Index: 4259846 (Open Web Text)

Max Activating Token Index: 322

Text #9

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.5079. Min Act: -0.1700

Data Index: 4110271 (Open Web Text)

Max Activating Token Index: 213

Text #10

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.4962. Min Act: -0.1700

Data Index: 6883408 (Open Web Text)

Max Activating Token Index: 330

Text #11

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.4966. Min Act: -0.1700

Data Index: 7747453 (Open Web Text)

Max Activating Token Index: 25

Text #12

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.5005. Min Act: -0.1700

Data Index: 4340471 (Open Web Text)

Max Activating Token Index: 23

Text #13

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.4954. Min Act: -0.1700

Data Index: 7864895 (Open Web Text)

Max Activating Token Index: 176

Text #14

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.4962. Min Act: -0.1695

Data Index: 8136075 (Open Web Text)

Max Activating Token Index: 62

Text #15

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.4913. Min Act: -0.1700

Data Index: 5502891 (Open Web Text)

Max Activating Token Index: 26

Text #16

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.5022. Min Act: -0.1700

Data Index: 3955165 (Open Web Text)

Max Activating Token Index: 704

Text #17

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.4952. Min Act: -0.1699

Data Index: 2470895 (Open Web Text)

Max Activating Token Index: 427

Text #18

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.4924. Min Act: -0.1700

Data Index: 6166732 (Open Web Text)

Max Activating Token Index: 698

Text #19

Max Range: 1.6401. Min Range: -1.6401

Max Act: 1.4907. Min Act: -0.1699

Data Index: 1883231 (Open Web Text)

Max Activating Token Index: 71