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

Dataset: Open Web Text

Neuron 34 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: 3.7988. Min Range: -3.7988

Max Act: 3.7988. Min Act: -0.1700

Data Index: 3909002 (Open Web Text)

Max Activating Token Index: 828

Text #1

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.7136. Min Act: -0.1700

Data Index: 274892 (Open Web Text)

Max Activating Token Index: 47

Text #2

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.6914. Min Act: -0.1700

Data Index: 1298633 (Open Web Text)

Max Activating Token Index: 147

Text #3

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.6887. Min Act: -0.1700

Data Index: 5729747 (Open Web Text)

Max Activating Token Index: 20

Text #4

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.6645. Min Act: -0.1700

Data Index: 178813 (Open Web Text)

Max Activating Token Index: 102

Text #5

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.6796. Min Act: -0.1700

Data Index: 263133 (Open Web Text)

Max Activating Token Index: 641

Text #6

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.6575. Min Act: -0.1700

Data Index: 178814 (Open Web Text)

Max Activating Token Index: 210

Text #7

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.6506. Min Act: -0.1700

Data Index: 8432228 (Open Web Text)

Max Activating Token Index: 573

Text #8

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.6263. Min Act: -0.1700

Data Index: 4314349 (Open Web Text)

Max Activating Token Index: 62

Text #9

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.6203. Min Act: -0.1700

Data Index: 2270659 (Open Web Text)

Max Activating Token Index: 42

Text #10

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.6312. Min Act: -0.1700

Data Index: 5608213 (Open Web Text)

Max Activating Token Index: 121

Text #11

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.5964. Min Act: -0.1700

Data Index: 1436658 (Open Web Text)

Max Activating Token Index: 210

Text #12

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.5988. Min Act: -0.1700

Data Index: 8068340 (Open Web Text)

Max Activating Token Index: 329

Text #13

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.5958. Min Act: -0.1700

Data Index: 399899 (Open Web Text)

Max Activating Token Index: 43

Text #14

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.6015. Min Act: -0.1700

Data Index: 7479007 (Open Web Text)

Max Activating Token Index: 850

Text #15

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.6045. Min Act: -0.1700

Data Index: 1051635 (Open Web Text)

Max Activating Token Index: 1015

Text #16

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.6097. Min Act: -0.1700

Data Index: 8116904 (Open Web Text)

Max Activating Token Index: 368

Text #17

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.5823. Min Act: -0.1700

Data Index: 3323257 (Open Web Text)

Max Activating Token Index: 269

Text #18

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.5884. Min Act: -0.1700

Data Index: 2378045 (Open Web Text)

Max Activating Token Index: 106

Text #19

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.5821. Min Act: -0.1700

Data Index: 7478995 (Open Web Text)

Max Activating Token Index: 701