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

Dataset: Open Web Text

Neuron 2777 in Layer 1

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: 0.6503. Min Range: -0.6503

Max Act: 0.6503. Min Act: -0.1700

Data Index: 1784714 (Open Web Text)

Max Activating Token Index: 346

Text #1

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.6305. Min Act: -0.1700

Data Index: 7561965 (Open Web Text)

Max Activating Token Index: 394

Text #2

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.6368. Min Act: -0.1700

Data Index: 2558764 (Open Web Text)

Max Activating Token Index: 388

Text #3

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.6274. Min Act: -0.1700

Data Index: 4375754 (Open Web Text)

Max Activating Token Index: 355

Text #4

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.6235. Min Act: -0.1700

Data Index: 3961086 (Open Web Text)

Max Activating Token Index: 356

Text #5

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.6358. Min Act: -0.1700

Data Index: 3209243 (Open Web Text)

Max Activating Token Index: 365

Text #6

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.6284. Min Act: -0.1700

Data Index: 4644397 (Open Web Text)

Max Activating Token Index: 381

Text #7

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.6402. Min Act: -0.1700

Data Index: 2168173 (Open Web Text)

Max Activating Token Index: 356

Text #8

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.6250. Min Act: -0.1700

Data Index: 2621602 (Open Web Text)

Max Activating Token Index: 357

Text #9

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.6232. Min Act: -0.1700

Data Index: 616260 (Open Web Text)

Max Activating Token Index: 375

Text #10

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.6245. Min Act: -0.1700

Data Index: 6740542 (Open Web Text)

Max Activating Token Index: 367

Text #11

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.6174. Min Act: -0.1700

Data Index: 8716819 (Open Web Text)

Max Activating Token Index: 345

Text #12

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.6141. Min Act: -0.1700

Data Index: 6000427 (Open Web Text)

Max Activating Token Index: 357

Text #13

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.6159. Min Act: -0.1700

Data Index: 6271909 (Open Web Text)

Max Activating Token Index: 342

Text #14

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.6241. Min Act: -0.1700

Data Index: 3448199 (Open Web Text)

Max Activating Token Index: 354

Text #15

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.6175. Min Act: -0.1700

Data Index: 3987753 (Open Web Text)

Max Activating Token Index: 372

Text #16

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.6109. Min Act: -0.1700

Data Index: 1803490 (Open Web Text)

Max Activating Token Index: 379

Text #17

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.6001. Min Act: -0.1700

Data Index: 4867697 (Open Web Text)

Max Activating Token Index: 375

Text #18

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.6065. Min Act: -0.1700

Data Index: 3267376 (Open Web Text)

Max Activating Token Index: 380

Text #19

Max Range: 0.6503. Min Range: -0.6503

Max Act: 0.6074. Min Act: -0.1700

Data Index: 6741893 (Open Web Text)

Max Activating Token Index: 389