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

Dataset: Open Web Text

Neuron 38 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: 5.8104. Min Range: -5.8104

Max Act: 5.8104. Min Act: -0.1700

Data Index: 6863941 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 5.8104. Min Range: -5.8104

Max Act: 5.7814. Min Act: -0.1700

Data Index: 577073 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 5.8104. Min Range: -5.8104

Max Act: 5.7827. Min Act: -0.1700

Data Index: 97808 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 5.8104. Min Range: -5.8104

Max Act: 5.7967. Min Act: -0.1700

Data Index: 3575053 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 5.8104. Min Range: -5.8104

Max Act: 5.7617. Min Act: -0.1700

Data Index: 3167538 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 5.8104. Min Range: -5.8104

Max Act: 5.7249. Min Act: -0.1700

Data Index: 271369 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 5.8104. Min Range: -5.8104

Max Act: 5.7178. Min Act: -0.1700

Data Index: 5043678 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 5.8104. Min Range: -5.8104

Max Act: 5.7342. Min Act: -0.1700

Data Index: 4053770 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 5.8104. Min Range: -5.8104

Max Act: 5.6882. Min Act: -0.1700

Data Index: 395938 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 5.8104. Min Range: -5.8104

Max Act: 5.7019. Min Act: -0.1700

Data Index: 6384996 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 5.8104. Min Range: -5.8104

Max Act: 5.6959. Min Act: -0.1700

Data Index: 2045875 (Open Web Text)

Max Activating Token Index: 12

Text #11

Max Range: 5.8104. Min Range: -5.8104

Max Act: 5.6843. Min Act: -0.1700

Data Index: 183902 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 5.8104. Min Range: -5.8104

Max Act: 5.6976. Min Act: -0.1700

Data Index: 3940459 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 5.8104. Min Range: -5.8104

Max Act: 5.6869. Min Act: -0.1700

Data Index: 8029092 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 5.8104. Min Range: -5.8104

Max Act: 5.7033. Min Act: -0.1700

Data Index: 1266268 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 5.8104. Min Range: -5.8104

Max Act: 5.6467. Min Act: -0.1700

Data Index: 4388965 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 5.8104. Min Range: -5.8104

Max Act: 5.6486. Min Act: -0.1700

Data Index: 2645242 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 5.8104. Min Range: -5.8104

Max Act: 5.6549. Min Act: -0.1700

Data Index: 3807289 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 5.8104. Min Range: -5.8104

Max Act: 5.6710. Min Act: -0.1700

Data Index: 5886380 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 5.8104. Min Range: -5.8104

Max Act: 5.6603. Min Act: -0.1700

Data Index: 183391 (Open Web Text)

Max Activating Token Index: 5