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

Dataset: Open Web Text

Neuron 214 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: 5.3148. Min Range: -5.3148

Max Act: 5.3148. Min Act: -0.1700

Data Index: 6295749 (Open Web Text)

Max Activating Token Index: 507

Text #1

Max Range: 5.3148. Min Range: -5.3148

Max Act: 5.2406. Min Act: -0.1700

Data Index: 7711451 (Open Web Text)

Max Activating Token Index: 352

Text #2

Max Range: 5.3148. Min Range: -5.3148

Max Act: 5.2008. Min Act: -0.1700

Data Index: 2106238 (Open Web Text)

Max Activating Token Index: 644

Text #3

Max Range: 5.3148. Min Range: -5.3148

Max Act: 5.1440. Min Act: -0.1700

Data Index: 1114041 (Open Web Text)

Max Activating Token Index: 82

Text #4

Max Range: 5.3148. Min Range: -5.3148

Max Act: 5.1815. Min Act: -0.1700

Data Index: 543189 (Open Web Text)

Max Activating Token Index: 524

Text #5

Max Range: 5.3148. Min Range: -5.3148

Max Act: 5.1232. Min Act: -0.1700

Data Index: 4477892 (Open Web Text)

Max Activating Token Index: 164

Text #6

Max Range: 5.3148. Min Range: -5.3148

Max Act: 5.0928. Min Act: -0.1699

Data Index: 3027832 (Open Web Text)

Max Activating Token Index: 561

Text #7

Max Range: 5.3148. Min Range: -5.3148

Max Act: 5.1317. Min Act: -0.1700

Data Index: 8701668 (Open Web Text)

Max Activating Token Index: 332

Text #8

Max Range: 5.3148. Min Range: -5.3148

Max Act: 5.0832. Min Act: -0.1700

Data Index: 253435 (Open Web Text)

Max Activating Token Index: 484

Text #9

Max Range: 5.3148. Min Range: -5.3148

Max Act: 5.0491. Min Act: -0.1700

Data Index: 370985 (Open Web Text)

Max Activating Token Index: 335

Text #10

Max Range: 5.3148. Min Range: -5.3148

Max Act: 5.0265. Min Act: -0.1700

Data Index: 6050491 (Open Web Text)

Max Activating Token Index: 303

Text #11

Max Range: 5.3148. Min Range: -5.3148

Max Act: 5.0177. Min Act: -0.1700

Data Index: 4936787 (Open Web Text)

Max Activating Token Index: 447

Text #12

Max Range: 5.3148. Min Range: -5.3148

Max Act: 5.0166. Min Act: -0.1700

Data Index: 3627572 (Open Web Text)

Max Activating Token Index: 788

Text #13

Max Range: 5.3148. Min Range: -5.3148

Max Act: 5.0141. Min Act: -0.1700

Data Index: 7391361 (Open Web Text)

Max Activating Token Index: 447

Text #14

Max Range: 5.3148. Min Range: -5.3148

Max Act: 5.0085. Min Act: -0.1700

Data Index: 1114039 (Open Web Text)

Max Activating Token Index: 30

Text #15

Max Range: 5.3148. Min Range: -5.3148

Max Act: 4.9539. Min Act: -0.1700

Data Index: 1176299 (Open Web Text)

Max Activating Token Index: 508

Text #16

Max Range: 5.3148. Min Range: -5.3148

Max Act: 4.9899. Min Act: -0.1700

Data Index: 3587599 (Open Web Text)

Max Activating Token Index: 977

Text #17

Max Range: 5.3148. Min Range: -5.3148

Max Act: 4.9964. Min Act: -0.1699

Data Index: 770499 (Open Web Text)

Max Activating Token Index: 654

Text #18

Max Range: 5.3148. Min Range: -5.3148

Max Act: 4.9573. Min Act: -0.1700

Data Index: 203630 (Open Web Text)

Max Activating Token Index: 841

Text #19

Max Range: 5.3148. Min Range: -5.3148

Max Act: 4.9882. Min Act: -0.1700

Data Index: 3526169 (Open Web Text)

Max Activating Token Index: 233