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

Dataset: Open Web Text

Neuron 72 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: 0.9275. Min Range: -0.9275

Max Act: 0.9275. Min Act: -0.1700

Data Index: 1608234 (Open Web Text)

Max Activating Token Index: 96

Text #1

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.9027. Min Act: -0.1700

Data Index: 541110 (Open Web Text)

Max Activating Token Index: 90

Text #2

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.8982. Min Act: -0.1700

Data Index: 8131916 (Open Web Text)

Max Activating Token Index: 97

Text #3

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.8995. Min Act: -0.1700

Data Index: 817297 (Open Web Text)

Max Activating Token Index: 99

Text #4

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.8932. Min Act: -0.1700

Data Index: 2767649 (Open Web Text)

Max Activating Token Index: 97

Text #5

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.8944. Min Act: -0.1700

Data Index: 8541958 (Open Web Text)

Max Activating Token Index: 92

Text #6

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.8937. Min Act: -0.1700

Data Index: 1127589 (Open Web Text)

Max Activating Token Index: 91

Text #7

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.8987. Min Act: -0.1700

Data Index: 2298194 (Open Web Text)

Max Activating Token Index: 92

Text #8

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.8925. Min Act: -0.1700

Data Index: 3448865 (Open Web Text)

Max Activating Token Index: 101

Text #9

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.8931. Min Act: -0.1700

Data Index: 2307993 (Open Web Text)

Max Activating Token Index: 100

Text #10

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.8870. Min Act: -0.1700

Data Index: 8528958 (Open Web Text)

Max Activating Token Index: 99

Text #11

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.8859. Min Act: -0.1700

Data Index: 1095063 (Open Web Text)

Max Activating Token Index: 92

Text #12

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.8844. Min Act: -0.1700

Data Index: 845047 (Open Web Text)

Max Activating Token Index: 99

Text #13

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.8868. Min Act: -0.1700

Data Index: 2411014 (Open Web Text)

Max Activating Token Index: 93

Text #14

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.8845. Min Act: -0.1700

Data Index: 8262287 (Open Web Text)

Max Activating Token Index: 95

Text #15

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.8828. Min Act: -0.1700

Data Index: 1947605 (Open Web Text)

Max Activating Token Index: 91

Text #16

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.8800. Min Act: -0.1700

Data Index: 6588468 (Open Web Text)

Max Activating Token Index: 96

Text #17

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.8846. Min Act: -0.1700

Data Index: 444727 (Open Web Text)

Max Activating Token Index: 96

Text #18

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.8768. Min Act: -0.1700

Data Index: 2462758 (Open Web Text)

Max Activating Token Index: 97

Text #19

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.8726. Min Act: -0.1700

Data Index: 734539 (Open Web Text)

Max Activating Token Index: 99