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

Dataset: Open Web Text

Neuron 2389 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: 3.7980. Min Range: -3.7980

Max Act: 3.7980. Min Act: -0.1700

Data Index: 6593455 (Open Web Text)

Max Activating Token Index: 21

Text #1

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.3790. Min Act: -0.1700

Data Index: 1920896 (Open Web Text)

Max Activating Token Index: 12

Text #2

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.3340. Min Act: -0.1700

Data Index: 617455 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.3340. Min Act: -0.1700

Data Index: 7341294 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.2036. Min Act: -0.1700

Data Index: 5887703 (Open Web Text)

Max Activating Token Index: 62

Text #5

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.1987. Min Act: -0.1700

Data Index: 2821580 (Open Web Text)

Max Activating Token Index: 283

Text #6

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.1823. Min Act: -0.1700

Data Index: 7247847 (Open Web Text)

Max Activating Token Index: 20

Text #7

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.1774. Min Act: -0.1700

Data Index: 696164 (Open Web Text)

Max Activating Token Index: 35

Text #8

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.1859. Min Act: -0.1700

Data Index: 6885786 (Open Web Text)

Max Activating Token Index: 27

Text #9

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.1766. Min Act: -0.1700

Data Index: 6049230 (Open Web Text)

Max Activating Token Index: 473

Text #10

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.1397. Min Act: -0.1700

Data Index: 1297635 (Open Web Text)

Max Activating Token Index: 26

Text #11

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.1448. Min Act: -0.1700

Data Index: 4900178 (Open Web Text)

Max Activating Token Index: 676

Text #12

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.1392. Min Act: -0.1700

Data Index: 5431356 (Open Web Text)

Max Activating Token Index: 384

Text #13

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.1294. Min Act: -0.1700

Data Index: 5798036 (Open Web Text)

Max Activating Token Index: 61

Text #14

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.1028. Min Act: -0.1700

Data Index: 4988534 (Open Web Text)

Max Activating Token Index: 252

Text #15

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.1004. Min Act: -0.1700

Data Index: 2103570 (Open Web Text)

Max Activating Token Index: 501

Text #16

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.1015. Min Act: -0.1700

Data Index: 5008311 (Open Web Text)

Max Activating Token Index: 26

Text #17

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.1094. Min Act: -0.1700

Data Index: 2028291 (Open Web Text)

Max Activating Token Index: 163

Text #18

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.0904. Min Act: -0.1700

Data Index: 609890 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 3.7980. Min Range: -3.7980

Max Act: 3.0967. Min Act: -0.1700

Data Index: 4796237 (Open Web Text)

Max Activating Token Index: 634