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

Dataset: Open Web Text

Neuron 3043 in Layer 2

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: 1.9777. Min Range: -1.9777

Max Act: 1.9777. Min Act: -0.1700

Data Index: 3561833 (Open Web Text)

Max Activating Token Index: 401

Text #1

Max Range: 1.9777. Min Range: -1.9777

Max Act: 1.9307. Min Act: -0.1700

Data Index: 6861346 (Open Web Text)

Max Activating Token Index: 527

Text #2

Max Range: 1.9777. Min Range: -1.9777

Max Act: 1.9324. Min Act: -0.1700

Data Index: 3656464 (Open Web Text)

Max Activating Token Index: 821

Text #3

Max Range: 1.9777. Min Range: -1.9777

Max Act: 1.9254. Min Act: -0.1700

Data Index: 4111158 (Open Web Text)

Max Activating Token Index: 413

Text #4

Max Range: 1.9777. Min Range: -1.9777

Max Act: 1.9355. Min Act: -0.1700

Data Index: 8743239 (Open Web Text)

Max Activating Token Index: 959

Text #5

Max Range: 1.9777. Min Range: -1.9777

Max Act: 1.9147. Min Act: -0.1700

Data Index: 6801725 (Open Web Text)

Max Activating Token Index: 738

Text #6

Max Range: 1.9777. Min Range: -1.9777

Max Act: 1.9102. Min Act: -0.1700

Data Index: 1694341 (Open Web Text)

Max Activating Token Index: 35

Text #7

Max Range: 1.9777. Min Range: -1.9777

Max Act: 1.9104. Min Act: -0.1700

Data Index: 4064116 (Open Web Text)

Max Activating Token Index: 530

Text #8

Max Range: 1.9777. Min Range: -1.9777

Max Act: 1.8980. Min Act: -0.1700

Data Index: 6069815 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 1.9777. Min Range: -1.9777

Max Act: 1.8973. Min Act: -0.1700

Data Index: 3900436 (Open Web Text)

Max Activating Token Index: 103

Text #10

Max Range: 1.9777. Min Range: -1.9777

Max Act: 1.8981. Min Act: -0.1700

Data Index: 6077507 (Open Web Text)

Max Activating Token Index: 225

Text #11

Max Range: 1.9777. Min Range: -1.9777

Max Act: 1.8930. Min Act: -0.1700

Data Index: 3258577 (Open Web Text)

Max Activating Token Index: 959

Text #12

Max Range: 1.9777. Min Range: -1.9777

Max Act: 1.8966. Min Act: -0.1700

Data Index: 2752462 (Open Web Text)

Max Activating Token Index: 88

Text #13

Max Range: 1.9777. Min Range: -1.9777

Max Act: 1.8821. Min Act: -0.1700

Data Index: 4548418 (Open Web Text)

Max Activating Token Index: 350

Text #14

Max Range: 1.9777. Min Range: -1.9777

Max Act: 1.8787. Min Act: -0.1700

Data Index: 3941183 (Open Web Text)

Max Activating Token Index: 679

Text #15

Max Range: 1.9777. Min Range: -1.9777

Max Act: 1.8932. Min Act: -0.1700

Data Index: 2036126 (Open Web Text)

Max Activating Token Index: 910

Text #16

Max Range: 1.9777. Min Range: -1.9777

Max Act: 1.8927. Min Act: -0.1700

Data Index: 7608782 (Open Web Text)

Max Activating Token Index: 585

Text #17

Max Range: 1.9777. Min Range: -1.9777

Max Act: 1.8669. Min Act: -0.1700

Data Index: 7333609 (Open Web Text)

Max Activating Token Index: 154

Text #18

Max Range: 1.9777. Min Range: -1.9777

Max Act: 1.8793. Min Act: -0.1700

Data Index: 5476449 (Open Web Text)

Max Activating Token Index: 535

Text #19

Max Range: 1.9777. Min Range: -1.9777

Max Act: 1.8826. Min Act: -0.1700

Data Index: 4772923 (Open Web Text)

Max Activating Token Index: 457