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

Dataset: Open Web Text

Neuron 264 in Layer 3

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: 3.7931. Min Range: -3.7931

Max Act: 3.7931. Min Act: -0.1700

Data Index: 601953 (Open Web Text)

Max Activating Token Index: 548

Text #1

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.6573. Min Act: -0.1700

Data Index: 7374691 (Open Web Text)

Max Activating Token Index: 34

Text #2

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.6910. Min Act: -0.1700

Data Index: 145059 (Open Web Text)

Max Activating Token Index: 228

Text #3

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.4822. Min Act: -0.1700

Data Index: 5271529 (Open Web Text)

Max Activating Token Index: 638

Text #4

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.4441. Min Act: -0.1700

Data Index: 5913482 (Open Web Text)

Max Activating Token Index: 870

Text #5

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.4016. Min Act: -0.1700

Data Index: 7672185 (Open Web Text)

Max Activating Token Index: 445

Text #6

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.4170. Min Act: -0.1700

Data Index: 4522210 (Open Web Text)

Max Activating Token Index: 727

Text #7

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.3929. Min Act: -0.1700

Data Index: 7483154 (Open Web Text)

Max Activating Token Index: 152

Text #8

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.4150. Min Act: -0.1700

Data Index: 8743262 (Open Web Text)

Max Activating Token Index: 142

Text #9

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.3327. Min Act: -0.1700

Data Index: 615705 (Open Web Text)

Max Activating Token Index: 455

Text #10

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.4008. Min Act: -0.1700

Data Index: 3638045 (Open Web Text)

Max Activating Token Index: 797

Text #11

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.3760. Min Act: -0.1700

Data Index: 1112822 (Open Web Text)

Max Activating Token Index: 105

Text #12

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.3605. Min Act: -0.1700

Data Index: 6966327 (Open Web Text)

Max Activating Token Index: 155

Text #13

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.3517. Min Act: -0.1700

Data Index: 4582542 (Open Web Text)

Max Activating Token Index: 901

Text #14

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.3353. Min Act: -0.1700

Data Index: 8662100 (Open Web Text)

Max Activating Token Index: 488

Text #15

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.3608. Min Act: -0.1700

Data Index: 7054184 (Open Web Text)

Max Activating Token Index: 288

Text #16

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.3504. Min Act: -0.1700

Data Index: 1615501 (Open Web Text)

Max Activating Token Index: 760

Text #17

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.3223. Min Act: -0.1700

Data Index: 3861518 (Open Web Text)

Max Activating Token Index: 149

Text #18

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.3525. Min Act: -0.1700

Data Index: 418198 (Open Web Text)

Max Activating Token Index: 417

Text #19

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.3825. Min Act: -0.1700

Data Index: 7864555 (Open Web Text)

Max Activating Token Index: 513