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

Dataset: Open Web Text

Neuron 2176 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: 4.0684. Min Range: -4.0684

Max Act: 4.0684. Min Act: -0.1700

Data Index: 8252301 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.9939. Min Act: -0.1700

Data Index: 5049862 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.9925. Min Act: -0.1700

Data Index: 10499 (Open Web Text)

Max Activating Token Index: 12

Text #3

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.9922. Min Act: -0.1700

Data Index: 1977630 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.9686. Min Act: -0.1700

Data Index: 2035204 (Open Web Text)

Max Activating Token Index: 40

Text #5

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.9625. Min Act: -0.1700

Data Index: 8240187 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.9498. Min Act: -0.1700

Data Index: 5037158 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.9432. Min Act: -0.1700

Data Index: 7067 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.9502. Min Act: -0.1700

Data Index: 1617806 (Open Web Text)

Max Activating Token Index: 102

Text #9

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.9365. Min Act: -0.1700

Data Index: 8036134 (Open Web Text)

Max Activating Token Index: 364

Text #10

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.9225. Min Act: -0.1700

Data Index: 2652235 (Open Web Text)

Max Activating Token Index: 61

Text #11

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.9387. Min Act: -0.1700

Data Index: 2522865 (Open Web Text)

Max Activating Token Index: 13

Text #12

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.9457. Min Act: -0.1700

Data Index: 2302682 (Open Web Text)

Max Activating Token Index: 11

Text #13

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.9093. Min Act: -0.1700

Data Index: 677236 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.9207. Min Act: -0.1700

Data Index: 5403036 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.9043. Min Act: -0.1700

Data Index: 8420079 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.8987. Min Act: -0.1700

Data Index: 4157709 (Open Web Text)

Max Activating Token Index: 35

Text #17

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.8883. Min Act: -0.1700

Data Index: 4797768 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.8635. Min Act: -0.1700

Data Index: 1162307 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 4.0684. Min Range: -4.0684

Max Act: 3.8909. Min Act: -0.1700

Data Index: 49368 (Open Web Text)

Max Activating Token Index: 7