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

Dataset: Open Web Text

Neuron 423 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: 4.2961. Min Range: -4.2961

Max Act: 4.2961. Min Act: -0.1700

Data Index: 2632624 (Open Web Text)

Max Activating Token Index: 985

Text #1

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.2506. Min Act: -0.1700

Data Index: 1485257 (Open Web Text)

Max Activating Token Index: 13

Text #2

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.2480. Min Act: -0.1700

Data Index: 5891070 (Open Web Text)

Max Activating Token Index: 24

Text #3

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.2790. Min Act: -0.1700

Data Index: 4306762 (Open Web Text)

Max Activating Token Index: 12

Text #4

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.2586. Min Act: -0.1700

Data Index: 7198733 (Open Web Text)

Max Activating Token Index: 34

Text #5

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.2159. Min Act: -0.1700

Data Index: 8134466 (Open Web Text)

Max Activating Token Index: 972

Text #6

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.1963. Min Act: -0.1700

Data Index: 287734 (Open Web Text)

Max Activating Token Index: 13

Text #7

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.1732. Min Act: -0.1700

Data Index: 8399508 (Open Web Text)

Max Activating Token Index: 1020

Text #8

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.1939. Min Act: -0.1700

Data Index: 7518084 (Open Web Text)

Max Activating Token Index: 208

Text #9

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.1533. Min Act: -0.1700

Data Index: 3563924 (Open Web Text)

Max Activating Token Index: 13

Text #10

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.1461. Min Act: -0.1700

Data Index: 5737614 (Open Web Text)

Max Activating Token Index: 64

Text #11

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.1508. Min Act: -0.1700

Data Index: 8598831 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.1622. Min Act: -0.1700

Data Index: 7482794 (Open Web Text)

Max Activating Token Index: 1015

Text #13

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.1588. Min Act: -0.1700

Data Index: 4536100 (Open Web Text)

Max Activating Token Index: 652

Text #14

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.1678. Min Act: -0.1700

Data Index: 6511000 (Open Web Text)

Max Activating Token Index: 57

Text #15

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.1411. Min Act: -0.1700

Data Index: 771005 (Open Web Text)

Max Activating Token Index: 972

Text #16

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.1608. Min Act: -0.1700

Data Index: 2697650 (Open Web Text)

Max Activating Token Index: 991

Text #17

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.1173. Min Act: -0.1700

Data Index: 4503769 (Open Web Text)

Max Activating Token Index: 369

Text #18

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.1267. Min Act: -0.1700

Data Index: 5782453 (Open Web Text)

Max Activating Token Index: 600

Text #19

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.1229. Min Act: -0.1700

Data Index: 5802050 (Open Web Text)

Max Activating Token Index: 962