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

Dataset: Open Web Text

Neuron 1400 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: 4.7862. Min Range: -4.7862

Max Act: 4.7844. Min Act: -0.1700

Data Index: 2464835 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 4.7862. Min Range: -4.7862

Max Act: 4.7862. Min Act: -0.1700

Data Index: 4121538 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 4.7862. Min Range: -4.7862

Max Act: 4.7862. Min Act: -0.1700

Data Index: 101010 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 4.7862. Min Range: -4.7862

Max Act: 4.7307. Min Act: -0.1700

Data Index: 471654 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 4.7862. Min Range: -4.7862

Max Act: 4.6930. Min Act: -0.1700

Data Index: 8819070 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.7862. Min Range: -4.7862

Max Act: 4.6798. Min Act: -0.1700

Data Index: 7334384 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.7862. Min Range: -4.7862

Max Act: 4.6714. Min Act: -0.1700

Data Index: 7090194 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.7862. Min Range: -4.7862

Max Act: 4.6383. Min Act: -0.1700

Data Index: 8415841 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.7862. Min Range: -4.7862

Max Act: 4.6529. Min Act: -0.1700

Data Index: 3750873 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 4.7862. Min Range: -4.7862

Max Act: 4.6512. Min Act: -0.1700

Data Index: 7300773 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 4.7862. Min Range: -4.7862

Max Act: 4.6363. Min Act: -0.1700

Data Index: 1131171 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 4.7862. Min Range: -4.7862

Max Act: 4.6406. Min Act: -0.1700

Data Index: 7019029 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 4.7862. Min Range: -4.7862

Max Act: 4.6414. Min Act: -0.1700

Data Index: 1531280 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 4.7862. Min Range: -4.7862

Max Act: 4.6095. Min Act: -0.1700

Data Index: 1129911 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.7862. Min Range: -4.7862

Max Act: 4.6216. Min Act: -0.1700

Data Index: 3447589 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 4.7862. Min Range: -4.7862

Max Act: 4.6272. Min Act: -0.1700

Data Index: 6257265 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 4.7862. Min Range: -4.7862

Max Act: 4.6074. Min Act: -0.1700

Data Index: 400689 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 4.7862. Min Range: -4.7862

Max Act: 4.6161. Min Act: -0.1700

Data Index: 8362264 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.7862. Min Range: -4.7862

Max Act: 4.6032. Min Act: -0.1700

Data Index: 2686247 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.7862. Min Range: -4.7862

Max Act: 4.6181. Min Act: -0.1700

Data Index: 2201759 (Open Web Text)

Max Activating Token Index: 5