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

Dataset: Open Web Text

Neuron 2362 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: 3.6272. Min Range: -3.6272

Max Act: 3.6272. Min Act: -0.1700

Data Index: 7244584 (Open Web Text)

Max Activating Token Index: 644

Text #1

Max Range: 3.6272. Min Range: -3.6272

Max Act: 3.5958. Min Act: -0.1700

Data Index: 7869497 (Open Web Text)

Max Activating Token Index: 462

Text #2

Max Range: 3.6272. Min Range: -3.6272

Max Act: 3.6116. Min Act: -0.1700

Data Index: 1386450 (Open Web Text)

Max Activating Token Index: 441

Text #3

Max Range: 3.6272. Min Range: -3.6272

Max Act: 3.5311. Min Act: -0.1700

Data Index: 7162896 (Open Web Text)

Max Activating Token Index: 265

Text #4

Max Range: 3.6272. Min Range: -3.6272

Max Act: 3.5202. Min Act: -0.1700

Data Index: 7960990 (Open Web Text)

Max Activating Token Index: 27

Text #5

Max Range: 3.6272. Min Range: -3.6272

Max Act: 3.4982. Min Act: -0.1700

Data Index: 2290891 (Open Web Text)

Max Activating Token Index: 916

Text #6

Max Range: 3.6272. Min Range: -3.6272

Max Act: 3.5161. Min Act: -0.1700

Data Index: 5585785 (Open Web Text)

Max Activating Token Index: 978

Text #7

Max Range: 3.6272. Min Range: -3.6272

Max Act: 3.5264. Min Act: -0.1700

Data Index: 1194483 (Open Web Text)

Max Activating Token Index: 576

Text #8

Max Range: 3.6272. Min Range: -3.6272

Max Act: 3.4750. Min Act: -0.1700

Data Index: 6439632 (Open Web Text)

Max Activating Token Index: 326

Text #9

Max Range: 3.6272. Min Range: -3.6272

Max Act: 3.4842. Min Act: -0.1700

Data Index: 8710411 (Open Web Text)

Max Activating Token Index: 260

Text #10

Max Range: 3.6272. Min Range: -3.6272

Max Act: 3.4574. Min Act: -0.1700

Data Index: 6586952 (Open Web Text)

Max Activating Token Index: 437

Text #11

Max Range: 3.6272. Min Range: -3.6272

Max Act: 3.4414. Min Act: -0.1700

Data Index: 7819644 (Open Web Text)

Max Activating Token Index: 591

Text #12

Max Range: 3.6272. Min Range: -3.6272

Max Act: 3.4336. Min Act: -0.1700

Data Index: 594818 (Open Web Text)

Max Activating Token Index: 283

Text #13

Max Range: 3.6272. Min Range: -3.6272

Max Act: 3.4271. Min Act: -0.1700

Data Index: 3438208 (Open Web Text)

Max Activating Token Index: 289

Text #14

Max Range: 3.6272. Min Range: -3.6272

Max Act: 3.4380. Min Act: -0.1700

Data Index: 4119005 (Open Web Text)

Max Activating Token Index: 366

Text #15

Max Range: 3.6272. Min Range: -3.6272

Max Act: 3.4590. Min Act: -0.1700

Data Index: 6050038 (Open Web Text)

Max Activating Token Index: 120

Text #16

Max Range: 3.6272. Min Range: -3.6272

Max Act: 3.4253. Min Act: -0.1700

Data Index: 7227328 (Open Web Text)

Max Activating Token Index: 939

Text #17

Max Range: 3.6272. Min Range: -3.6272

Max Act: 3.4269. Min Act: -0.1700

Data Index: 6678744 (Open Web Text)

Max Activating Token Index: 320

Text #18

Max Range: 3.6272. Min Range: -3.6272

Max Act: 3.4223. Min Act: -0.1700

Data Index: 4614192 (Open Web Text)

Max Activating Token Index: 958

Text #19

Max Range: 3.6272. Min Range: -3.6272

Max Act: 3.3962. Min Act: -0.1700

Data Index: 3272079 (Open Web Text)

Max Activating Token Index: 741