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

Dataset: Open Web Text

Neuron 32 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: 4.4062. Min Range: -4.4062

Max Act: 4.4043. Min Act: -0.1700

Data Index: 7019862 (Open Web Text)

Max Activating Token Index: 196

Text #1

Max Range: 4.4062. Min Range: -4.4062

Max Act: 4.3927. Min Act: -0.1700

Data Index: 2476458 (Open Web Text)

Max Activating Token Index: 664

Text #2

Max Range: 4.4062. Min Range: -4.4062

Max Act: 4.4059. Min Act: -0.1700

Data Index: 1123556 (Open Web Text)

Max Activating Token Index: 402

Text #3

Max Range: 4.4062. Min Range: -4.4062

Max Act: 4.4062. Min Act: -0.1700

Data Index: 6798633 (Open Web Text)

Max Activating Token Index: 606

Text #4

Max Range: 4.4062. Min Range: -4.4062

Max Act: 4.3288. Min Act: -0.1700

Data Index: 4307908 (Open Web Text)

Max Activating Token Index: 55

Text #5

Max Range: 4.4062. Min Range: -4.4062

Max Act: 4.3614. Min Act: -0.1700

Data Index: 2544658 (Open Web Text)

Max Activating Token Index: 531

Text #6

Max Range: 4.4062. Min Range: -4.4062

Max Act: 4.3074. Min Act: -0.1700

Data Index: 3817338 (Open Web Text)

Max Activating Token Index: 69

Text #7

Max Range: 4.4062. Min Range: -4.4062

Max Act: 4.2828. Min Act: -0.1700

Data Index: 7353777 (Open Web Text)

Max Activating Token Index: 157

Text #8

Max Range: 4.4062. Min Range: -4.4062

Max Act: 4.3075. Min Act: -0.1700

Data Index: 4279253 (Open Web Text)

Max Activating Token Index: 645

Text #9

Max Range: 4.4062. Min Range: -4.4062

Max Act: 4.2926. Min Act: -0.1700

Data Index: 8159305 (Open Web Text)

Max Activating Token Index: 656

Text #10

Max Range: 4.4062. Min Range: -4.4062

Max Act: 4.3087. Min Act: -0.1700

Data Index: 874855 (Open Web Text)

Max Activating Token Index: 470

Text #11

Max Range: 4.4062. Min Range: -4.4062

Max Act: 4.2811. Min Act: -0.1700

Data Index: 5980152 (Open Web Text)

Max Activating Token Index: 228

Text #12

Max Range: 4.4062. Min Range: -4.4062

Max Act: 4.3341. Min Act: -0.1700

Data Index: 1598040 (Open Web Text)

Max Activating Token Index: 917

Text #13

Max Range: 4.4062. Min Range: -4.4062

Max Act: 4.2559. Min Act: -0.1700

Data Index: 3419577 (Open Web Text)

Max Activating Token Index: 380

Text #14

Max Range: 4.4062. Min Range: -4.4062

Max Act: 4.2438. Min Act: -0.1700

Data Index: 6554075 (Open Web Text)

Max Activating Token Index: 795

Text #15

Max Range: 4.4062. Min Range: -4.4062

Max Act: 4.2714. Min Act: -0.1700

Data Index: 8017654 (Open Web Text)

Max Activating Token Index: 746

Text #16

Max Range: 4.4062. Min Range: -4.4062

Max Act: 4.2221. Min Act: -0.1700

Data Index: 2424441 (Open Web Text)

Max Activating Token Index: 736

Text #17

Max Range: 4.4062. Min Range: -4.4062

Max Act: 4.2570. Min Act: -0.1700

Data Index: 456776 (Open Web Text)

Max Activating Token Index: 51

Text #18

Max Range: 4.4062. Min Range: -4.4062

Max Act: 4.2403. Min Act: -0.1700

Data Index: 1541595 (Open Web Text)

Max Activating Token Index: 930

Text #19

Max Range: 4.4062. Min Range: -4.4062

Max Act: 4.2205. Min Act: -0.1700

Data Index: 2122298 (Open Web Text)

Max Activating Token Index: 67