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

Dataset: Open Web Text

Neuron 2025 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: 2.4470. Min Range: -2.4470

Max Act: 2.4470. Min Act: -0.1700

Data Index: 6584960 (Open Web Text)

Max Activating Token Index: 306

Text #1

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.3240. Min Act: -0.1700

Data Index: 3175902 (Open Web Text)

Max Activating Token Index: 835

Text #2

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.2886. Min Act: -0.1700

Data Index: 8190167 (Open Web Text)

Max Activating Token Index: 888

Text #3

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.2963. Min Act: -0.1700

Data Index: 4207321 (Open Web Text)

Max Activating Token Index: 290

Text #4

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.2680. Min Act: -0.1700

Data Index: 209624 (Open Web Text)

Max Activating Token Index: 280

Text #5

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.2506. Min Act: -0.1700

Data Index: 7595018 (Open Web Text)

Max Activating Token Index: 277

Text #6

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.2510. Min Act: -0.1700

Data Index: 905129 (Open Web Text)

Max Activating Token Index: 280

Text #7

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.2228. Min Act: -0.1700

Data Index: 2523773 (Open Web Text)

Max Activating Token Index: 873

Text #8

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.2180. Min Act: -0.1700

Data Index: 930722 (Open Web Text)

Max Activating Token Index: 823

Text #9

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.1924. Min Act: -0.1700

Data Index: 4382610 (Open Web Text)

Max Activating Token Index: 882

Text #10

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.2029. Min Act: -0.1700

Data Index: 877483 (Open Web Text)

Max Activating Token Index: 837

Text #11

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.1963. Min Act: -0.1700

Data Index: 3391754 (Open Web Text)

Max Activating Token Index: 283

Text #12

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.1996. Min Act: -0.1700

Data Index: 2666579 (Open Web Text)

Max Activating Token Index: 253

Text #13

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.1992. Min Act: -0.1700

Data Index: 1678555 (Open Web Text)

Max Activating Token Index: 275

Text #14

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.2054. Min Act: -0.1700

Data Index: 6164035 (Open Web Text)

Max Activating Token Index: 278

Text #15

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.2088. Min Act: -0.1700

Data Index: 8251981 (Open Web Text)

Max Activating Token Index: 886

Text #16

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.1981. Min Act: -0.1700

Data Index: 1932213 (Open Web Text)

Max Activating Token Index: 847

Text #17

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.1611. Min Act: -0.1700

Data Index: 1103149 (Open Web Text)

Max Activating Token Index: 875

Text #18

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.1746. Min Act: -0.1700

Data Index: 3695749 (Open Web Text)

Max Activating Token Index: 888

Text #19

Max Range: 2.4470. Min Range: -2.4470

Max Act: 2.1630. Min Act: -0.1700

Data Index: 4165711 (Open Web Text)

Max Activating Token Index: 297