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

Dataset: Open Web Text

Neuron 508 in Layer 2

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: 4.2906. Min Range: -4.2906

Max Act: 4.2906. Min Act: -0.1700

Data Index: 6697501 (Open Web Text)

Max Activating Token Index: 419

Text #1

Max Range: 4.2906. Min Range: -4.2906

Max Act: 4.1496. Min Act: -0.1700

Data Index: 3197744 (Open Web Text)

Max Activating Token Index: 205

Text #2

Max Range: 4.2906. Min Range: -4.2906

Max Act: 4.1605. Min Act: -0.1700

Data Index: 3315041 (Open Web Text)

Max Activating Token Index: 14

Text #3

Max Range: 4.2906. Min Range: -4.2906

Max Act: 4.1289. Min Act: -0.1700

Data Index: 3310819 (Open Web Text)

Max Activating Token Index: 631

Text #4

Max Range: 4.2906. Min Range: -4.2906

Max Act: 4.0723. Min Act: -0.1700

Data Index: 23562 (Open Web Text)

Max Activating Token Index: 416

Text #5

Max Range: 4.2906. Min Range: -4.2906

Max Act: 4.1022. Min Act: -0.1700

Data Index: 3647901 (Open Web Text)

Max Activating Token Index: 19

Text #6

Max Range: 4.2906. Min Range: -4.2906

Max Act: 4.0733. Min Act: -0.1700

Data Index: 762619 (Open Web Text)

Max Activating Token Index: 113

Text #7

Max Range: 4.2906. Min Range: -4.2906

Max Act: 4.0933. Min Act: -0.1700

Data Index: 4520396 (Open Web Text)

Max Activating Token Index: 267

Text #8

Max Range: 4.2906. Min Range: -4.2906

Max Act: 4.0418. Min Act: -0.1700

Data Index: 5367936 (Open Web Text)

Max Activating Token Index: 778

Text #9

Max Range: 4.2906. Min Range: -4.2906

Max Act: 4.0534. Min Act: -0.1700

Data Index: 6737285 (Open Web Text)

Max Activating Token Index: 41

Text #10

Max Range: 4.2906. Min Range: -4.2906

Max Act: 3.9965. Min Act: -0.1700

Data Index: 6836785 (Open Web Text)

Max Activating Token Index: 40

Text #11

Max Range: 4.2906. Min Range: -4.2906

Max Act: 3.9957. Min Act: -0.1700

Data Index: 3197743 (Open Web Text)

Max Activating Token Index: 500

Text #12

Max Range: 4.2906. Min Range: -4.2906

Max Act: 3.9738. Min Act: -0.1700

Data Index: 1223843 (Open Web Text)

Max Activating Token Index: 469

Text #13

Max Range: 4.2906. Min Range: -4.2906

Max Act: 4.0067. Min Act: -0.1700

Data Index: 8618585 (Open Web Text)

Max Activating Token Index: 164

Text #14

Max Range: 4.2906. Min Range: -4.2906

Max Act: 3.9814. Min Act: -0.1700

Data Index: 7666887 (Open Web Text)

Max Activating Token Index: 446

Text #15

Max Range: 4.2906. Min Range: -4.2906

Max Act: 3.9897. Min Act: -0.1700

Data Index: 3279677 (Open Web Text)

Max Activating Token Index: 258

Text #16

Max Range: 4.2906. Min Range: -4.2906

Max Act: 3.9726. Min Act: -0.1700

Data Index: 2328709 (Open Web Text)

Max Activating Token Index: 321

Text #17

Max Range: 4.2906. Min Range: -4.2906

Max Act: 3.9469. Min Act: -0.1700

Data Index: 226268 (Open Web Text)

Max Activating Token Index: 44

Text #18

Max Range: 4.2906. Min Range: -4.2906

Max Act: 3.9495. Min Act: -0.1700

Data Index: 3362431 (Open Web Text)

Max Activating Token Index: 36

Text #19

Max Range: 4.2906. Min Range: -4.2906

Max Act: 3.9413. Min Act: -0.1700

Data Index: 5475953 (Open Web Text)

Max Activating Token Index: 126