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

Dataset: Open Web Text

Neuron 577 in Layer 0

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: 4.4609. Min Range: -4.4609

Max Act: 4.4333. Min Act: -0.1700

Data Index: 1112873 (Open Web Text)

Max Activating Token Index: 44

Text #1

Max Range: 4.4609. Min Range: -4.4609

Max Act: 4.4534. Min Act: -0.1700

Data Index: 3165173 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.4609. Min Range: -4.4609

Max Act: 4.4609. Min Act: -0.1700

Data Index: 5871106 (Open Web Text)

Max Activating Token Index: 37

Text #3

Max Range: 4.4609. Min Range: -4.4609

Max Act: 4.3985. Min Act: -0.1700

Data Index: 5087981 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 4.4609. Min Range: -4.4609

Max Act: 4.4027. Min Act: -0.1700

Data Index: 2745641 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 4.4609. Min Range: -4.4609

Max Act: 4.3918. Min Act: -0.1700

Data Index: 2057751 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 4.4609. Min Range: -4.4609

Max Act: 4.3630. Min Act: -0.1700

Data Index: 4068711 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 4.4609. Min Range: -4.4609

Max Act: 4.3788. Min Act: -0.1700

Data Index: 834742 (Open Web Text)

Max Activating Token Index: 14

Text #8

Max Range: 4.4609. Min Range: -4.4609

Max Act: 4.3905. Min Act: -0.1700

Data Index: 402984 (Open Web Text)

Max Activating Token Index: 10

Text #9

Max Range: 4.4609. Min Range: -4.4609

Max Act: 4.3663. Min Act: -0.1700

Data Index: 3386713 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 4.4609. Min Range: -4.4609

Max Act: 4.3661. Min Act: -0.1700

Data Index: 5988744 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 4.4609. Min Range: -4.4609

Max Act: 4.3896. Min Act: -0.1700

Data Index: 5724998 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 4.4609. Min Range: -4.4609

Max Act: 4.3739. Min Act: -0.1700

Data Index: 8358870 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.4609. Min Range: -4.4609

Max Act: 4.3872. Min Act: -0.1700

Data Index: 5648353 (Open Web Text)

Max Activating Token Index: 10

Text #14

Max Range: 4.4609. Min Range: -4.4609

Max Act: 4.3367. Min Act: -0.1700

Data Index: 717325 (Open Web Text)

Max Activating Token Index: 69

Text #15

Max Range: 4.4609. Min Range: -4.4609

Max Act: 4.3401. Min Act: -0.1700

Data Index: 8027961 (Open Web Text)

Max Activating Token Index: 12

Text #16

Max Range: 4.4609. Min Range: -4.4609

Max Act: 4.3499. Min Act: -0.1700

Data Index: 3340897 (Open Web Text)

Max Activating Token Index: 928

Text #17

Max Range: 4.4609. Min Range: -4.4609

Max Act: 4.3343. Min Act: -0.1700

Data Index: 2021680 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 4.4609. Min Range: -4.4609

Max Act: 4.3548. Min Act: -0.1700

Data Index: 6316279 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 4.4609. Min Range: -4.4609

Max Act: 4.3680. Min Act: -0.1700

Data Index: 5970574 (Open Web Text)

Max Activating Token Index: 3