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

Dataset: Open Web Text

Neuron 557 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: 2.6537. Min Range: -2.6537

Max Act: 2.6537. Min Act: -0.1700

Data Index: 1383875 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.6537. Min Range: -2.6537

Max Act: 2.6329. Min Act: -0.1700

Data Index: 2636291 (Open Web Text)

Max Activating Token Index: 909

Text #2

Max Range: 2.6537. Min Range: -2.6537

Max Act: 2.6141. Min Act: -0.1700

Data Index: 4026276 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 2.6537. Min Range: -2.6537

Max Act: 2.6173. Min Act: -0.1700

Data Index: 1763879 (Open Web Text)

Max Activating Token Index: 122

Text #4

Max Range: 2.6537. Min Range: -2.6537

Max Act: 2.6121. Min Act: -0.1700

Data Index: 2636292 (Open Web Text)

Max Activating Token Index: 370

Text #5

Max Range: 2.6537. Min Range: -2.6537

Max Act: 2.6069. Min Act: -0.1700

Data Index: 7673716 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 2.6537. Min Range: -2.6537

Max Act: 2.6245. Min Act: -0.1700

Data Index: 5185752 (Open Web Text)

Max Activating Token Index: 26

Text #7

Max Range: 2.6537. Min Range: -2.6537

Max Act: 2.5970. Min Act: -0.1700

Data Index: 5023654 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 2.6537. Min Range: -2.6537

Max Act: 2.5928. Min Act: -0.1700

Data Index: 8146236 (Open Web Text)

Max Activating Token Index: 10

Text #9

Max Range: 2.6537. Min Range: -2.6537

Max Act: 2.5956. Min Act: -0.1700

Data Index: 5581221 (Open Web Text)

Max Activating Token Index: 25

Text #10

Max Range: 2.6537. Min Range: -2.6537

Max Act: 2.6031. Min Act: -0.1700

Data Index: 2557014 (Open Web Text)

Max Activating Token Index: 32

Text #11

Max Range: 2.6537. Min Range: -2.6537

Max Act: 2.5993. Min Act: -0.1700

Data Index: 4721037 (Open Web Text)

Max Activating Token Index: 682

Text #12

Max Range: 2.6537. Min Range: -2.6537

Max Act: 2.6017. Min Act: -0.1700

Data Index: 7910719 (Open Web Text)

Max Activating Token Index: 539

Text #13

Max Range: 2.6537. Min Range: -2.6537

Max Act: 2.6016. Min Act: -0.1700

Data Index: 4363982 (Open Web Text)

Max Activating Token Index: 12

Text #14

Max Range: 2.6537. Min Range: -2.6537

Max Act: 2.6069. Min Act: -0.1700

Data Index: 4107702 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 2.6537. Min Range: -2.6537

Max Act: 2.5983. Min Act: -0.1700

Data Index: 7573261 (Open Web Text)

Max Activating Token Index: 16

Text #16

Max Range: 2.6537. Min Range: -2.6537

Max Act: 2.5899. Min Act: -0.1700

Data Index: 6071680 (Open Web Text)

Max Activating Token Index: 20

Text #17

Max Range: 2.6537. Min Range: -2.6537

Max Act: 2.5864. Min Act: -0.1700

Data Index: 3884384 (Open Web Text)

Max Activating Token Index: 140

Text #18

Max Range: 2.6537. Min Range: -2.6537

Max Act: 2.5940. Min Act: -0.1700

Data Index: 6348420 (Open Web Text)

Max Activating Token Index: 28

Text #19

Max Range: 2.6537. Min Range: -2.6537

Max Act: 2.5857. Min Act: -0.1700

Data Index: 7340227 (Open Web Text)

Max Activating Token Index: 16