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

Dataset: Open Web Text

Neuron 947 in Layer 1

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: 1.7033. Min Range: -1.7033

Max Act: 1.7033. Min Act: -0.1700

Data Index: 2347668 (Open Web Text)

Max Activating Token Index: 435

Text #1

Max Range: 1.7033. Min Range: -1.7033

Max Act: 1.6094. Min Act: -0.1700

Data Index: 5558793 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 1.7033. Min Range: -1.7033

Max Act: 1.5999. Min Act: -0.1700

Data Index: 2479126 (Open Web Text)

Max Activating Token Index: 15

Text #3

Max Range: 1.7033. Min Range: -1.7033

Max Act: 1.5990. Min Act: -0.1698

Data Index: 6215849 (Open Web Text)

Max Activating Token Index: 86

Text #4

Max Range: 1.7033. Min Range: -1.7033

Max Act: 1.5948. Min Act: -0.1700

Data Index: 7586909 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 1.7033. Min Range: -1.7033

Max Act: 1.5858. Min Act: -0.1700

Data Index: 802809 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 1.7033. Min Range: -1.7033

Max Act: 1.5950. Min Act: -0.1700

Data Index: 5869338 (Open Web Text)

Max Activating Token Index: 18

Text #7

Max Range: 1.7033. Min Range: -1.7033

Max Act: 1.5903. Min Act: -0.1700

Data Index: 5173321 (Open Web Text)

Max Activating Token Index: 27

Text #8

Max Range: 1.7033. Min Range: -1.7033

Max Act: 1.5874. Min Act: -0.1700

Data Index: 2694447 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 1.7033. Min Range: -1.7033

Max Act: 1.5756. Min Act: -0.1633

Data Index: 6007467 (Open Web Text)

Max Activating Token Index: 102

Text #10

Max Range: 1.7033. Min Range: -1.7033

Max Act: 1.5762. Min Act: -0.1693

Data Index: 6366998 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 1.7033. Min Range: -1.7033

Max Act: 1.5570. Min Act: -0.1700

Data Index: 4382690 (Open Web Text)

Max Activating Token Index: 302

Text #12

Max Range: 1.7033. Min Range: -1.7033

Max Act: 1.5709. Min Act: -0.1688

Data Index: 866671 (Open Web Text)

Max Activating Token Index: 39

Text #13

Max Range: 1.7033. Min Range: -1.7033

Max Act: 1.5627. Min Act: -0.1700

Data Index: 5180271 (Open Web Text)

Max Activating Token Index: 53

Text #14

Max Range: 1.7033. Min Range: -1.7033

Max Act: 1.5660. Min Act: -0.1700

Data Index: 2550407 (Open Web Text)

Max Activating Token Index: 234

Text #15

Max Range: 1.7033. Min Range: -1.7033

Max Act: 1.5726. Min Act: -0.1700

Data Index: 1859575 (Open Web Text)

Max Activating Token Index: 123

Text #16

Max Range: 1.7033. Min Range: -1.7033

Max Act: 1.5608. Min Act: -0.1700

Data Index: 5612275 (Open Web Text)

Max Activating Token Index: 275

Text #17

Max Range: 1.7033. Min Range: -1.7033

Max Act: 1.5621. Min Act: -0.1700

Data Index: 2490371 (Open Web Text)

Max Activating Token Index: 266

Text #18

Max Range: 1.7033. Min Range: -1.7033

Max Act: 1.5608. Min Act: -0.1700

Data Index: 989720 (Open Web Text)

Max Activating Token Index: 80

Text #19

Max Range: 1.7033. Min Range: -1.7033

Max Act: 1.5721. Min Act: -0.1700

Data Index: 6465625 (Open Web Text)

Max Activating Token Index: 13