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

Dataset: Open Web Text

Neuron 586 in Layer 4

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: 4.8223. Min Range: -4.8223

Max Act: 4.8223. Min Act: -0.1700

Data Index: 8061658 (Open Web Text)

Max Activating Token Index: 178

Text #1

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.8050. Min Act: -0.1700

Data Index: 7471972 (Open Web Text)

Max Activating Token Index: 192

Text #2

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.7691. Min Act: -0.1700

Data Index: 5327661 (Open Web Text)

Max Activating Token Index: 462

Text #3

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.7471. Min Act: -0.1700

Data Index: 6673107 (Open Web Text)

Max Activating Token Index: 464

Text #4

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.7720. Min Act: -0.1700

Data Index: 5019020 (Open Web Text)

Max Activating Token Index: 504

Text #5

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.7670. Min Act: -0.1700

Data Index: 60211 (Open Web Text)

Max Activating Token Index: 167

Text #6

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.7212. Min Act: -0.1700

Data Index: 1737316 (Open Web Text)

Max Activating Token Index: 422

Text #7

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.6980. Min Act: -0.1700

Data Index: 431826 (Open Web Text)

Max Activating Token Index: 364

Text #8

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.7026. Min Act: -0.1700

Data Index: 1931210 (Open Web Text)

Max Activating Token Index: 369

Text #9

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.7182. Min Act: -0.1700

Data Index: 5713908 (Open Web Text)

Max Activating Token Index: 225

Text #10

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.7089. Min Act: -0.1700

Data Index: 8532110 (Open Web Text)

Max Activating Token Index: 377

Text #11

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.7034. Min Act: -0.1700

Data Index: 5119666 (Open Web Text)

Max Activating Token Index: 202

Text #12

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.6567. Min Act: -0.1700

Data Index: 1778189 (Open Web Text)

Max Activating Token Index: 449

Text #13

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.6524. Min Act: -0.1700

Data Index: 1687357 (Open Web Text)

Max Activating Token Index: 462

Text #14

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.6776. Min Act: -0.1700

Data Index: 8347010 (Open Web Text)

Max Activating Token Index: 133

Text #15

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.6757. Min Act: -0.1700

Data Index: 7060891 (Open Web Text)

Max Activating Token Index: 989

Text #16

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.6956. Min Act: -0.1700

Data Index: 3078814 (Open Web Text)

Max Activating Token Index: 665

Text #17

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.6763. Min Act: -0.1700

Data Index: 4711947 (Open Web Text)

Max Activating Token Index: 462

Text #18

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.6746. Min Act: -0.1700

Data Index: 5877745 (Open Web Text)

Max Activating Token Index: 148

Text #19

Max Range: 4.8223. Min Range: -4.8223

Max Act: 4.6601. Min Act: -0.1700

Data Index: 3901959 (Open Web Text)

Max Activating Token Index: 987