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

Dataset: Open Web Text

Neuron 2091 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: 3.2992. Min Range: -3.2992

Max Act: 3.2992. Min Act: -0.1700

Data Index: 1634469 (Open Web Text)

Max Activating Token Index: 331

Text #1

Max Range: 3.2992. Min Range: -3.2992

Max Act: 3.2759. Min Act: -0.1700

Data Index: 7423772 (Open Web Text)

Max Activating Token Index: 161

Text #2

Max Range: 3.2992. Min Range: -3.2992

Max Act: 3.2498. Min Act: -0.1700

Data Index: 3575622 (Open Web Text)

Max Activating Token Index: 240

Text #3

Max Range: 3.2992. Min Range: -3.2992

Max Act: 3.2816. Min Act: -0.1700

Data Index: 5257169 (Open Web Text)

Max Activating Token Index: 540

Text #4

Max Range: 3.2992. Min Range: -3.2992

Max Act: 3.2431. Min Act: -0.1700

Data Index: 2324794 (Open Web Text)

Max Activating Token Index: 125

Text #5

Max Range: 3.2992. Min Range: -3.2992

Max Act: 3.2608. Min Act: -0.1700

Data Index: 3744751 (Open Web Text)

Max Activating Token Index: 236

Text #6

Max Range: 3.2992. Min Range: -3.2992

Max Act: 3.2015. Min Act: -0.1700

Data Index: 7075825 (Open Web Text)

Max Activating Token Index: 352

Text #7

Max Range: 3.2992. Min Range: -3.2992

Max Act: 3.2192. Min Act: -0.1700

Data Index: 6381897 (Open Web Text)

Max Activating Token Index: 811

Text #8

Max Range: 3.2992. Min Range: -3.2992

Max Act: 3.2402. Min Act: -0.1700

Data Index: 7630949 (Open Web Text)

Max Activating Token Index: 114

Text #9

Max Range: 3.2992. Min Range: -3.2992

Max Act: 3.1971. Min Act: -0.1700

Data Index: 1805065 (Open Web Text)

Max Activating Token Index: 482

Text #10

Max Range: 3.2992. Min Range: -3.2992

Max Act: 3.2323. Min Act: -0.1700

Data Index: 367544 (Open Web Text)

Max Activating Token Index: 272

Text #11

Max Range: 3.2992. Min Range: -3.2992

Max Act: 3.2020. Min Act: -0.1700

Data Index: 980211 (Open Web Text)

Max Activating Token Index: 157

Text #12

Max Range: 3.2992. Min Range: -3.2992

Max Act: 3.2363. Min Act: -0.1700

Data Index: 7442960 (Open Web Text)

Max Activating Token Index: 258

Text #13

Max Range: 3.2992. Min Range: -3.2992

Max Act: 3.1946. Min Act: -0.1700

Data Index: 3070631 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 3.2992. Min Range: -3.2992

Max Act: 3.1925. Min Act: -0.1700

Data Index: 3827047 (Open Web Text)

Max Activating Token Index: 476

Text #15

Max Range: 3.2992. Min Range: -3.2992

Max Act: 3.2301. Min Act: -0.1700

Data Index: 6659868 (Open Web Text)

Max Activating Token Index: 228

Text #16

Max Range: 3.2992. Min Range: -3.2992

Max Act: 3.2110. Min Act: -0.1700

Data Index: 4373227 (Open Web Text)

Max Activating Token Index: 355

Text #17

Max Range: 3.2992. Min Range: -3.2992

Max Act: 3.1933. Min Act: -0.1700

Data Index: 4296453 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.2992. Min Range: -3.2992

Max Act: 3.1838. Min Act: -0.1700

Data Index: 7315902 (Open Web Text)

Max Activating Token Index: 487

Text #19

Max Range: 3.2992. Min Range: -3.2992

Max Act: 3.1946. Min Act: -0.1700

Data Index: 3147964 (Open Web Text)

Max Activating Token Index: 908