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

Dataset: Open Web Text

Neuron 1973 in Layer 3

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: 5.5996. Min Range: -5.5996

Max Act: 5.5996. Min Act: -0.1700

Data Index: 2015728 (Open Web Text)

Max Activating Token Index: 209

Text #1

Max Range: 5.5996. Min Range: -5.5996

Max Act: 5.1759. Min Act: -0.1700

Data Index: 4045162 (Open Web Text)

Max Activating Token Index: 330

Text #2

Max Range: 5.5996. Min Range: -5.5996

Max Act: 5.2027. Min Act: -0.1698

Data Index: 5553754 (Open Web Text)

Max Activating Token Index: 231

Text #3

Max Range: 5.5996. Min Range: -5.5996

Max Act: 5.1693. Min Act: -0.1700

Data Index: 8383402 (Open Web Text)

Max Activating Token Index: 24

Text #4

Max Range: 5.5996. Min Range: -5.5996

Max Act: 5.1007. Min Act: -0.1700

Data Index: 4000886 (Open Web Text)

Max Activating Token Index: 152

Text #5

Max Range: 5.5996. Min Range: -5.5996

Max Act: 5.0140. Min Act: -0.1700

Data Index: 5421114 (Open Web Text)

Max Activating Token Index: 993

Text #6

Max Range: 5.5996. Min Range: -5.5996

Max Act: 5.0480. Min Act: -0.1700

Data Index: 930353 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 5.5996. Min Range: -5.5996

Max Act: 4.9591. Min Act: -0.1700

Data Index: 7034161 (Open Web Text)

Max Activating Token Index: 338

Text #8

Max Range: 5.5996. Min Range: -5.5996

Max Act: 4.9621. Min Act: -0.1700

Data Index: 5905568 (Open Web Text)

Max Activating Token Index: 224

Text #9

Max Range: 5.5996. Min Range: -5.5996

Max Act: 4.9527. Min Act: -0.1700

Data Index: 2637885 (Open Web Text)

Max Activating Token Index: 321

Text #10

Max Range: 5.5996. Min Range: -5.5996

Max Act: 4.9505. Min Act: -0.1700

Data Index: 6696804 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 5.5996. Min Range: -5.5996

Max Act: 4.9409. Min Act: -0.1700

Data Index: 99518 (Open Web Text)

Max Activating Token Index: 195

Text #12

Max Range: 5.5996. Min Range: -5.5996

Max Act: 4.9014. Min Act: -0.1700

Data Index: 839632 (Open Web Text)

Max Activating Token Index: 552

Text #13

Max Range: 5.5996. Min Range: -5.5996

Max Act: 4.8945. Min Act: -0.1700

Data Index: 5763927 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 5.5996. Min Range: -5.5996

Max Act: 4.9181. Min Act: -0.1683

Data Index: 8118388 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 5.5996. Min Range: -5.5996

Max Act: 4.9322. Min Act: -0.1700

Data Index: 5360598 (Open Web Text)

Max Activating Token Index: 26

Text #16

Max Range: 5.5996. Min Range: -5.5996

Max Act: 4.8945. Min Act: -0.1700

Data Index: 6243352 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 5.5996. Min Range: -5.5996

Max Act: 4.9456. Min Act: -0.1700

Data Index: 477652 (Open Web Text)

Max Activating Token Index: 883

Text #18

Max Range: 5.5996. Min Range: -5.5996

Max Act: 4.8943. Min Act: -0.1700

Data Index: 8386120 (Open Web Text)

Max Activating Token Index: 23

Text #19

Max Range: 5.5996. Min Range: -5.5996

Max Act: 4.9650. Min Act: -0.1700

Data Index: 923780 (Open Web Text)

Max Activating Token Index: 8