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

Dataset: Open Web Text

Neuron 2173 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: 3.9409. Min Range: -3.9409

Max Act: 3.9409. Min Act: -0.1700

Data Index: 1423893 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.9383. Min Act: -0.1700

Data Index: 2765092 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.8889. Min Act: -0.1700

Data Index: 2326203 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.8965. Min Act: -0.1700

Data Index: 1383720 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.8911. Min Act: -0.1700

Data Index: 6335220 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.9027. Min Act: -0.1700

Data Index: 2625791 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.8922. Min Act: -0.1700

Data Index: 1102729 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.8661. Min Act: -0.1700

Data Index: 4444796 (Open Web Text)

Max Activating Token Index: 10

Text #8

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.8786. Min Act: -0.1700

Data Index: 8128982 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.8803. Min Act: -0.1700

Data Index: 7039744 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.8543. Min Act: -0.1700

Data Index: 6445396 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.8860. Min Act: -0.1700

Data Index: 1912836 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.8552. Min Act: -0.1700

Data Index: 5283715 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.8664. Min Act: -0.1700

Data Index: 5233747 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.8794. Min Act: -0.1700

Data Index: 4983825 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.8746. Min Act: -0.1700

Data Index: 4256740 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.8533. Min Act: -0.1700

Data Index: 677135 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.8556. Min Act: -0.1700

Data Index: 3872129 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.8670. Min Act: -0.1700

Data Index: 2035154 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.9409. Min Range: -3.9409

Max Act: 3.8740. Min Act: -0.1700

Data Index: 1175859 (Open Web Text)

Max Activating Token Index: 8