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

Dataset: Open Web Text

Neuron 1632 in Layer 6

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: 4.6855. Min Range: -4.6855

Max Act: 4.6855. Min Act: -0.1700

Data Index: 56807 (Open Web Text)

Max Activating Token Index: 88

Text #1

Max Range: 4.6855. Min Range: -4.6855

Max Act: 4.5624. Min Act: -0.1700

Data Index: 6820136 (Open Web Text)

Max Activating Token Index: 283

Text #2

Max Range: 4.6855. Min Range: -4.6855

Max Act: 4.5857. Min Act: -0.1700

Data Index: 2543068 (Open Web Text)

Max Activating Token Index: 53

Text #3

Max Range: 4.6855. Min Range: -4.6855

Max Act: 4.5381. Min Act: -0.1700

Data Index: 5670516 (Open Web Text)

Max Activating Token Index: 321

Text #4

Max Range: 4.6855. Min Range: -4.6855

Max Act: 4.5636. Min Act: -0.1700

Data Index: 2118933 (Open Web Text)

Max Activating Token Index: 370

Text #5

Max Range: 4.6855. Min Range: -4.6855

Max Act: 4.5055. Min Act: -0.1700

Data Index: 3154036 (Open Web Text)

Max Activating Token Index: 415

Text #6

Max Range: 4.6855. Min Range: -4.6855

Max Act: 4.5106. Min Act: -0.1700

Data Index: 1016572 (Open Web Text)

Max Activating Token Index: 699

Text #7

Max Range: 4.6855. Min Range: -4.6855

Max Act: 4.4692. Min Act: -0.1700

Data Index: 4825721 (Open Web Text)

Max Activating Token Index: 145

Text #8

Max Range: 4.6855. Min Range: -4.6855

Max Act: 4.4200. Min Act: -0.1700

Data Index: 618314 (Open Web Text)

Max Activating Token Index: 672

Text #9

Max Range: 4.6855. Min Range: -4.6855

Max Act: 4.4106. Min Act: -0.1700

Data Index: 3956383 (Open Web Text)

Max Activating Token Index: 340

Text #10

Max Range: 4.6855. Min Range: -4.6855

Max Act: 4.4250. Min Act: -0.1700

Data Index: 7037980 (Open Web Text)

Max Activating Token Index: 826

Text #11

Max Range: 4.6855. Min Range: -4.6855

Max Act: 4.4016. Min Act: -0.1700

Data Index: 6311695 (Open Web Text)

Max Activating Token Index: 569

Text #12

Max Range: 4.6855. Min Range: -4.6855

Max Act: 4.3891. Min Act: -0.1700

Data Index: 2158907 (Open Web Text)

Max Activating Token Index: 657

Text #13

Max Range: 4.6855. Min Range: -4.6855

Max Act: 4.3700. Min Act: -0.1700

Data Index: 7232200 (Open Web Text)

Max Activating Token Index: 756

Text #14

Max Range: 4.6855. Min Range: -4.6855

Max Act: 4.3577. Min Act: -0.1700

Data Index: 3091759 (Open Web Text)

Max Activating Token Index: 31

Text #15

Max Range: 4.6855. Min Range: -4.6855

Max Act: 4.3579. Min Act: -0.1700

Data Index: 1741281 (Open Web Text)

Max Activating Token Index: 104

Text #16

Max Range: 4.6855. Min Range: -4.6855

Max Act: 4.3688. Min Act: -0.1700

Data Index: 3027121 (Open Web Text)

Max Activating Token Index: 218

Text #17

Max Range: 4.6855. Min Range: -4.6855

Max Act: 4.3331. Min Act: -0.1700

Data Index: 6215828 (Open Web Text)

Max Activating Token Index: 746

Text #18

Max Range: 4.6855. Min Range: -4.6855

Max Act: 4.3375. Min Act: -0.1700

Data Index: 3262506 (Open Web Text)

Max Activating Token Index: 268

Text #19

Max Range: 4.6855. Min Range: -4.6855

Max Act: 4.3396. Min Act: -0.1700

Data Index: 1316717 (Open Web Text)

Max Activating Token Index: 9