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

Dataset: Open Web Text

Neuron 2966 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: 1.4861. Min Range: -1.4861

Max Act: 1.4861. Min Act: -0.1700

Data Index: 6455757 (Open Web Text)

Max Activating Token Index: 557

Text #1

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.4556. Min Act: -0.1700

Data Index: 3003683 (Open Web Text)

Max Activating Token Index: 220

Text #2

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.4562. Min Act: -0.1700

Data Index: 4384162 (Open Web Text)

Max Activating Token Index: 53

Text #3

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.4021. Min Act: -0.1700

Data Index: 1041345 (Open Web Text)

Max Activating Token Index: 406

Text #4

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.4089. Min Act: -0.1698

Data Index: 2532610 (Open Web Text)

Max Activating Token Index: 12

Text #5

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.3968. Min Act: -0.1698

Data Index: 763273 (Open Web Text)

Max Activating Token Index: 462

Text #6

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.3983. Min Act: -0.1680

Data Index: 2079317 (Open Web Text)

Max Activating Token Index: 759

Text #7

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.3870. Min Act: -0.1693

Data Index: 3987680 (Open Web Text)

Max Activating Token Index: 372

Text #8

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.3892. Min Act: -0.1700

Data Index: 6097070 (Open Web Text)

Max Activating Token Index: 547

Text #9

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.3842. Min Act: -0.1700

Data Index: 4613927 (Open Web Text)

Max Activating Token Index: 465

Text #10

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.3918. Min Act: -0.1700

Data Index: 3888122 (Open Web Text)

Max Activating Token Index: 267

Text #11

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.3792. Min Act: -0.1700

Data Index: 5237745 (Open Web Text)

Max Activating Token Index: 56

Text #12

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.3757. Min Act: -0.1700

Data Index: 6266336 (Open Web Text)

Max Activating Token Index: 637

Text #13

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.3785. Min Act: -0.1700

Data Index: 2949470 (Open Web Text)

Max Activating Token Index: 212

Text #14

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.3748. Min Act: -0.1700

Data Index: 277253 (Open Web Text)

Max Activating Token Index: 263

Text #15

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.3801. Min Act: -0.1700

Data Index: 6469429 (Open Web Text)

Max Activating Token Index: 66

Text #16

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.3731. Min Act: -0.1700

Data Index: 5171066 (Open Web Text)

Max Activating Token Index: 287

Text #17

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.3737. Min Act: -0.1698

Data Index: 2988442 (Open Web Text)

Max Activating Token Index: 505

Text #18

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.3740. Min Act: -0.1700

Data Index: 1043326 (Open Web Text)

Max Activating Token Index: 180

Text #19

Max Range: 1.4861. Min Range: -1.4861

Max Act: 1.3613. Min Act: -0.1700

Data Index: 3024733 (Open Web Text)

Max Activating Token Index: 670