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

Dataset: Open Web Text

Neuron 1802 in Layer 2

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: 2.6081. Min Range: -2.6081

Max Act: 2.6075. Min Act: -0.1700

Data Index: 7805838 (Open Web Text)

Max Activating Token Index: 93

Text #1

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.6081. Min Act: -0.1700

Data Index: 3512169 (Open Web Text)

Max Activating Token Index: 469

Text #2

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.5754. Min Act: -0.1700

Data Index: 7558181 (Open Web Text)

Max Activating Token Index: 444

Text #3

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.5857. Min Act: -0.1700

Data Index: 920240 (Open Web Text)

Max Activating Token Index: 320

Text #4

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.5788. Min Act: -0.1700

Data Index: 8700792 (Open Web Text)

Max Activating Token Index: 779

Text #5

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.5442. Min Act: -0.1700

Data Index: 4096498 (Open Web Text)

Max Activating Token Index: 719

Text #6

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.5501. Min Act: -0.1700

Data Index: 5548316 (Open Web Text)

Max Activating Token Index: 385

Text #7

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.5377. Min Act: -0.1700

Data Index: 677739 (Open Web Text)

Max Activating Token Index: 769

Text #8

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.5170. Min Act: -0.1700

Data Index: 3557557 (Open Web Text)

Max Activating Token Index: 323

Text #9

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.5110. Min Act: -0.1700

Data Index: 2868626 (Open Web Text)

Max Activating Token Index: 351

Text #10

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.5127. Min Act: -0.1700

Data Index: 5507256 (Open Web Text)

Max Activating Token Index: 199

Text #11

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.5030. Min Act: -0.1700

Data Index: 1668926 (Open Web Text)

Max Activating Token Index: 929

Text #12

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.4930. Min Act: -0.1700

Data Index: 1957637 (Open Web Text)

Max Activating Token Index: 806

Text #13

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.4820. Min Act: -0.1700

Data Index: 8830739 (Open Web Text)

Max Activating Token Index: 190

Text #14

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.4932. Min Act: -0.1700

Data Index: 1232984 (Open Web Text)

Max Activating Token Index: 378

Text #15

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.5028. Min Act: -0.1700

Data Index: 6450094 (Open Web Text)

Max Activating Token Index: 552

Text #16

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.4911. Min Act: -0.1700

Data Index: 5583578 (Open Web Text)

Max Activating Token Index: 17

Text #17

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.4687. Min Act: -0.1700

Data Index: 7244323 (Open Web Text)

Max Activating Token Index: 926

Text #18

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.4736. Min Act: -0.1700

Data Index: 4112492 (Open Web Text)

Max Activating Token Index: 200

Text #19

Max Range: 2.6081. Min Range: -2.6081

Max Act: 2.4741. Min Act: -0.1700

Data Index: 7039799 (Open Web Text)

Max Activating Token Index: 138