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

Dataset: Open Web Text

Neuron 20 in Layer 4

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: 4.7033. Min Range: -4.7033

Max Act: 4.7033. Min Act: -0.1700

Data Index: 3641920 (Open Web Text)

Max Activating Token Index: 678

Text #1

Max Range: 4.7033. Min Range: -4.7033

Max Act: 4.5597. Min Act: -0.1700

Data Index: 2798257 (Open Web Text)

Max Activating Token Index: 92

Text #2

Max Range: 4.7033. Min Range: -4.7033

Max Act: 4.5146. Min Act: -0.1700

Data Index: 1064182 (Open Web Text)

Max Activating Token Index: 247

Text #3

Max Range: 4.7033. Min Range: -4.7033

Max Act: 4.5160. Min Act: -0.1700

Data Index: 2802610 (Open Web Text)

Max Activating Token Index: 476

Text #4

Max Range: 4.7033. Min Range: -4.7033

Max Act: 4.4637. Min Act: -0.1700

Data Index: 4401904 (Open Web Text)

Max Activating Token Index: 228

Text #5

Max Range: 4.7033. Min Range: -4.7033

Max Act: 4.4772. Min Act: -0.1700

Data Index: 672449 (Open Web Text)

Max Activating Token Index: 12

Text #6

Max Range: 4.7033. Min Range: -4.7033

Max Act: 4.4568. Min Act: -0.1700

Data Index: 4951583 (Open Web Text)

Max Activating Token Index: 768

Text #7

Max Range: 4.7033. Min Range: -4.7033

Max Act: 4.4375. Min Act: -0.1700

Data Index: 2824036 (Open Web Text)

Max Activating Token Index: 295

Text #8

Max Range: 4.7033. Min Range: -4.7033

Max Act: 4.4753. Min Act: -0.1700

Data Index: 598207 (Open Web Text)

Max Activating Token Index: 890

Text #9

Max Range: 4.7033. Min Range: -4.7033

Max Act: 4.4308. Min Act: -0.1700

Data Index: 1146750 (Open Web Text)

Max Activating Token Index: 117

Text #10

Max Range: 4.7033. Min Range: -4.7033

Max Act: 4.4632. Min Act: -0.1700

Data Index: 1491556 (Open Web Text)

Max Activating Token Index: 521

Text #11

Max Range: 4.7033. Min Range: -4.7033

Max Act: 4.4181. Min Act: -0.1700

Data Index: 6479692 (Open Web Text)

Max Activating Token Index: 920

Text #12

Max Range: 4.7033. Min Range: -4.7033

Max Act: 4.4469. Min Act: -0.1700

Data Index: 8554828 (Open Web Text)

Max Activating Token Index: 936

Text #13

Max Range: 4.7033. Min Range: -4.7033

Max Act: 4.4252. Min Act: -0.1700

Data Index: 3772375 (Open Web Text)

Max Activating Token Index: 491

Text #14

Max Range: 4.7033. Min Range: -4.7033

Max Act: 4.3884. Min Act: -0.1700

Data Index: 7316260 (Open Web Text)

Max Activating Token Index: 187

Text #15

Max Range: 4.7033. Min Range: -4.7033

Max Act: 4.3910. Min Act: -0.1700

Data Index: 4595578 (Open Web Text)

Max Activating Token Index: 831

Text #16

Max Range: 4.7033. Min Range: -4.7033

Max Act: 4.3939. Min Act: -0.1700

Data Index: 7729144 (Open Web Text)

Max Activating Token Index: 178

Text #17

Max Range: 4.7033. Min Range: -4.7033

Max Act: 4.3824. Min Act: -0.1700

Data Index: 1924796 (Open Web Text)

Max Activating Token Index: 238

Text #18

Max Range: 4.7033. Min Range: -4.7033

Max Act: 4.4225. Min Act: -0.1700

Data Index: 7134362 (Open Web Text)

Max Activating Token Index: 346

Text #19

Max Range: 4.7033. Min Range: -4.7033

Max Act: 4.3646. Min Act: -0.1700

Data Index: 1718512 (Open Web Text)

Max Activating Token Index: 909