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

Dataset: Open Web Text

Neuron 1575 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: 1.8470. Min Range: -1.8470

Max Act: 1.8470. Min Act: -0.1700

Data Index: 6577961 (Open Web Text)

Max Activating Token Index: 635

Text #1

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.7442. Min Act: -0.1699

Data Index: 4283867 (Open Web Text)

Max Activating Token Index: 133

Text #2

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.7127. Min Act: -0.1700

Data Index: 6520089 (Open Web Text)

Max Activating Token Index: 119

Text #3

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.6777. Min Act: -0.1699

Data Index: 1056070 (Open Web Text)

Max Activating Token Index: 65

Text #4

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.6756. Min Act: -0.1700

Data Index: 468985 (Open Web Text)

Max Activating Token Index: 791

Text #5

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.6723. Min Act: -0.1700

Data Index: 5794440 (Open Web Text)

Max Activating Token Index: 436

Text #6

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.6661. Min Act: -0.1700

Data Index: 4659447 (Open Web Text)

Max Activating Token Index: 326

Text #7

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.6868. Min Act: -0.1700

Data Index: 409350 (Open Web Text)

Max Activating Token Index: 349

Text #8

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.6606. Min Act: -0.1700

Data Index: 374955 (Open Web Text)

Max Activating Token Index: 316

Text #9

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.6673. Min Act: -0.1700

Data Index: 5511202 (Open Web Text)

Max Activating Token Index: 102

Text #10

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.6430. Min Act: -0.1700

Data Index: 2380325 (Open Web Text)

Max Activating Token Index: 381

Text #11

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.6427. Min Act: -0.1700

Data Index: 8491592 (Open Web Text)

Max Activating Token Index: 701

Text #12

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.6440. Min Act: -0.1700

Data Index: 7286177 (Open Web Text)

Max Activating Token Index: 955

Text #13

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.6435. Min Act: -0.1700

Data Index: 6852745 (Open Web Text)

Max Activating Token Index: 981

Text #14

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.6411. Min Act: -0.1700

Data Index: 7923734 (Open Web Text)

Max Activating Token Index: 116

Text #15

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.6376. Min Act: -0.1700

Data Index: 4739593 (Open Web Text)

Max Activating Token Index: 48

Text #16

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.6282. Min Act: -0.1700

Data Index: 136048 (Open Web Text)

Max Activating Token Index: 698

Text #17

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.6403. Min Act: -0.1700

Data Index: 6966967 (Open Web Text)

Max Activating Token Index: 239

Text #18

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.6308. Min Act: -0.1700

Data Index: 1498956 (Open Web Text)

Max Activating Token Index: 867

Text #19

Max Range: 1.8470. Min Range: -1.8470

Max Act: 1.6339. Min Act: -0.1700

Data Index: 3247594 (Open Web Text)

Max Activating Token Index: 932