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

Dataset: Open Web Text

Neuron 2203 in Layer 0

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: 4.1984. Min Range: -4.1984

Max Act: 4.1984. Min Act: -0.1700

Data Index: 4041552 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 4.1984. Min Range: -4.1984

Max Act: 4.1364. Min Act: -0.1700

Data Index: 7082549 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 4.1984. Min Range: -4.1984

Max Act: 4.1454. Min Act: -0.1700

Data Index: 8351125 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 4.1984. Min Range: -4.1984

Max Act: 4.1263. Min Act: -0.1700

Data Index: 269712 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.1984. Min Range: -4.1984

Max Act: 4.1068. Min Act: -0.1700

Data Index: 4837544 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 4.1984. Min Range: -4.1984

Max Act: 4.0987. Min Act: -0.1700

Data Index: 4400769 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.1984. Min Range: -4.1984

Max Act: 4.0949. Min Act: -0.1700

Data Index: 2474201 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 4.1984. Min Range: -4.1984

Max Act: 4.0884. Min Act: -0.1700

Data Index: 649555 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 4.1984. Min Range: -4.1984

Max Act: 4.1068. Min Act: -0.1700

Data Index: 7641245 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 4.1984. Min Range: -4.1984

Max Act: 4.0956. Min Act: -0.1700

Data Index: 3973044 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 4.1984. Min Range: -4.1984

Max Act: 4.1068. Min Act: -0.1700

Data Index: 102494 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 4.1984. Min Range: -4.1984

Max Act: 4.0638. Min Act: -0.1700

Data Index: 7284422 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 4.1984. Min Range: -4.1984

Max Act: 4.0412. Min Act: -0.1700

Data Index: 2449443 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.1984. Min Range: -4.1984

Max Act: 4.0572. Min Act: -0.1700

Data Index: 2151038 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 4.1984. Min Range: -4.1984

Max Act: 4.0769. Min Act: -0.1700

Data Index: 3074367 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.1984. Min Range: -4.1984

Max Act: 4.0638. Min Act: -0.1700

Data Index: 4216913 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 4.1984. Min Range: -4.1984

Max Act: 4.0654. Min Act: -0.1700

Data Index: 5144902 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.1984. Min Range: -4.1984

Max Act: 4.0675. Min Act: -0.1700

Data Index: 1099544 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.1984. Min Range: -4.1984

Max Act: 4.0175. Min Act: -0.1700

Data Index: 5153889 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 4.1984. Min Range: -4.1984

Max Act: 4.0158. Min Act: -0.1700

Data Index: 5604714 (Open Web Text)

Max Activating Token Index: 6