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

Dataset: Open Web Text

Neuron 307 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: 3.4477. Min Range: -3.4477

Max Act: 3.4477. Min Act: -0.1700

Data Index: 6873136 (Open Web Text)

Max Activating Token Index: 536

Text #1

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.4175. Min Act: -0.1700

Data Index: 1106830 (Open Web Text)

Max Activating Token Index: 534

Text #2

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.4137. Min Act: -0.1700

Data Index: 7123052 (Open Web Text)

Max Activating Token Index: 53

Text #3

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.4016. Min Act: -0.1700

Data Index: 4246761 (Open Web Text)

Max Activating Token Index: 321

Text #4

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.4076. Min Act: -0.1700

Data Index: 7302045 (Open Web Text)

Max Activating Token Index: 489

Text #5

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.3570. Min Act: -0.1700

Data Index: 8221037 (Open Web Text)

Max Activating Token Index: 487

Text #6

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.3422. Min Act: -0.1700

Data Index: 991581 (Open Web Text)

Max Activating Token Index: 389

Text #7

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.3318. Min Act: -0.1700

Data Index: 7047474 (Open Web Text)

Max Activating Token Index: 13

Text #8

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.3315. Min Act: -0.1700

Data Index: 2479197 (Open Web Text)

Max Activating Token Index: 24

Text #9

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.3337. Min Act: -0.1700

Data Index: 2661137 (Open Web Text)

Max Activating Token Index: 457

Text #10

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.3121. Min Act: -0.1700

Data Index: 6097232 (Open Web Text)

Max Activating Token Index: 262

Text #11

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.3144. Min Act: -0.1700

Data Index: 8585629 (Open Web Text)

Max Activating Token Index: 549

Text #12

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.2899. Min Act: -0.1700

Data Index: 8109874 (Open Web Text)

Max Activating Token Index: 84

Text #13

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.2859. Min Act: -0.1700

Data Index: 5968924 (Open Web Text)

Max Activating Token Index: 578

Text #14

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.2914. Min Act: -0.1700

Data Index: 7260795 (Open Web Text)

Max Activating Token Index: 93

Text #15

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.2955. Min Act: -0.1700

Data Index: 6436482 (Open Web Text)

Max Activating Token Index: 54

Text #16

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.2936. Min Act: -0.1700

Data Index: 7031723 (Open Web Text)

Max Activating Token Index: 111

Text #17

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.3015. Min Act: -0.1700

Data Index: 8499709 (Open Web Text)

Max Activating Token Index: 386

Text #18

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.2843. Min Act: -0.1700

Data Index: 2055847 (Open Web Text)

Max Activating Token Index: 314

Text #19

Max Range: 3.4477. Min Range: -3.4477

Max Act: 3.2933. Min Act: -0.1700

Data Index: 7832909 (Open Web Text)

Max Activating Token Index: 551