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

Dataset: Open Web Text

Neuron 2404 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: 4.4184. Min Range: -4.4184

Max Act: 4.4184. Min Act: -0.1700

Data Index: 1122369 (Open Web Text)

Max Activating Token Index: 93

Text #1

Max Range: 4.4184. Min Range: -4.4184

Max Act: 4.4104. Min Act: -0.1700

Data Index: 5907200 (Open Web Text)

Max Activating Token Index: 47

Text #2

Max Range: 4.4184. Min Range: -4.4184

Max Act: 4.3795. Min Act: -0.1700

Data Index: 66875 (Open Web Text)

Max Activating Token Index: 100

Text #3

Max Range: 4.4184. Min Range: -4.4184

Max Act: 4.3695. Min Act: -0.1700

Data Index: 6410220 (Open Web Text)

Max Activating Token Index: 40

Text #4

Max Range: 4.4184. Min Range: -4.4184

Max Act: 4.3878. Min Act: -0.1700

Data Index: 4959521 (Open Web Text)

Max Activating Token Index: 42

Text #5

Max Range: 4.4184. Min Range: -4.4184

Max Act: 4.3782. Min Act: -0.1700

Data Index: 8063533 (Open Web Text)

Max Activating Token Index: 31

Text #6

Max Range: 4.4184. Min Range: -4.4184

Max Act: 4.3618. Min Act: -0.1700

Data Index: 1733940 (Open Web Text)

Max Activating Token Index: 432

Text #7

Max Range: 4.4184. Min Range: -4.4184

Max Act: 4.3321. Min Act: -0.1700

Data Index: 6148012 (Open Web Text)

Max Activating Token Index: 51

Text #8

Max Range: 4.4184. Min Range: -4.4184

Max Act: 4.3440. Min Act: -0.1700

Data Index: 5523494 (Open Web Text)

Max Activating Token Index: 29

Text #9

Max Range: 4.4184. Min Range: -4.4184

Max Act: 4.3288. Min Act: -0.1700

Data Index: 8184215 (Open Web Text)

Max Activating Token Index: 181

Text #10

Max Range: 4.4184. Min Range: -4.4184

Max Act: 4.3402. Min Act: -0.1700

Data Index: 4287788 (Open Web Text)

Max Activating Token Index: 51

Text #11

Max Range: 4.4184. Min Range: -4.4184

Max Act: 4.3365. Min Act: -0.1700

Data Index: 4163781 (Open Web Text)

Max Activating Token Index: 106

Text #12

Max Range: 4.4184. Min Range: -4.4184

Max Act: 4.3491. Min Act: -0.1700

Data Index: 795567 (Open Web Text)

Max Activating Token Index: 248

Text #13

Max Range: 4.4184. Min Range: -4.4184

Max Act: 4.3662. Min Act: -0.1700

Data Index: 7668370 (Open Web Text)

Max Activating Token Index: 330

Text #14

Max Range: 4.4184. Min Range: -4.4184

Max Act: 4.3309. Min Act: -0.1700

Data Index: 2018532 (Open Web Text)

Max Activating Token Index: 246

Text #15

Max Range: 4.4184. Min Range: -4.4184

Max Act: 4.3455. Min Act: -0.1700

Data Index: 1800651 (Open Web Text)

Max Activating Token Index: 52

Text #16

Max Range: 4.4184. Min Range: -4.4184

Max Act: 4.3175. Min Act: -0.1700

Data Index: 6566699 (Open Web Text)

Max Activating Token Index: 857

Text #17

Max Range: 4.4184. Min Range: -4.4184

Max Act: 4.3310. Min Act: -0.1700

Data Index: 13302 (Open Web Text)

Max Activating Token Index: 351

Text #18

Max Range: 4.4184. Min Range: -4.4184

Max Act: 4.3023. Min Act: -0.1700

Data Index: 5806852 (Open Web Text)

Max Activating Token Index: 37

Text #19

Max Range: 4.4184. Min Range: -4.4184

Max Act: 4.3193. Min Act: -0.1700

Data Index: 1568104 (Open Web Text)

Max Activating Token Index: 42