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

Dataset: Open Web Text

Neuron 274 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: 4.7238. Min Range: -4.7238

Max Act: 4.6895. Min Act: -0.1700

Data Index: 440912 (Open Web Text)

Max Activating Token Index: 246

Text #1

Max Range: 4.7238. Min Range: -4.7238

Max Act: 4.7238. Min Act: -0.1700

Data Index: 2640541 (Open Web Text)

Max Activating Token Index: 319

Text #2

Max Range: 4.7238. Min Range: -4.7238

Max Act: 4.6007. Min Act: -0.1700

Data Index: 1765451 (Open Web Text)

Max Activating Token Index: 158

Text #3

Max Range: 4.7238. Min Range: -4.7238

Max Act: 4.5149. Min Act: -0.1700

Data Index: 7509256 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 4.7238. Min Range: -4.7238

Max Act: 4.5277. Min Act: -0.1700

Data Index: 1787977 (Open Web Text)

Max Activating Token Index: 96

Text #5

Max Range: 4.7238. Min Range: -4.7238

Max Act: 4.4851. Min Act: -0.1700

Data Index: 8094541 (Open Web Text)

Max Activating Token Index: 478

Text #6

Max Range: 4.7238. Min Range: -4.7238

Max Act: 4.5275. Min Act: -0.1700

Data Index: 6093725 (Open Web Text)

Max Activating Token Index: 950

Text #7

Max Range: 4.7238. Min Range: -4.7238

Max Act: 4.5266. Min Act: -0.1700

Data Index: 5229798 (Open Web Text)

Max Activating Token Index: 552

Text #8

Max Range: 4.7238. Min Range: -4.7238

Max Act: 4.4855. Min Act: -0.1700

Data Index: 5187837 (Open Web Text)

Max Activating Token Index: 839

Text #9

Max Range: 4.7238. Min Range: -4.7238

Max Act: 4.4317. Min Act: -0.1700

Data Index: 799276 (Open Web Text)

Max Activating Token Index: 61

Text #10

Max Range: 4.7238. Min Range: -4.7238

Max Act: 4.4623. Min Act: -0.1700

Data Index: 4711027 (Open Web Text)

Max Activating Token Index: 386

Text #11

Max Range: 4.7238. Min Range: -4.7238

Max Act: 4.4803. Min Act: -0.1700

Data Index: 2130702 (Open Web Text)

Max Activating Token Index: 365

Text #12

Max Range: 4.7238. Min Range: -4.7238

Max Act: 4.4913. Min Act: -0.1700

Data Index: 2194525 (Open Web Text)

Max Activating Token Index: 454

Text #13

Max Range: 4.7238. Min Range: -4.7238

Max Act: 4.5241. Min Act: -0.1700

Data Index: 4691093 (Open Web Text)

Max Activating Token Index: 635

Text #14

Max Range: 4.7238. Min Range: -4.7238

Max Act: 4.4733. Min Act: -0.1700

Data Index: 1188392 (Open Web Text)

Max Activating Token Index: 44

Text #15

Max Range: 4.7238. Min Range: -4.7238

Max Act: 4.4600. Min Act: -0.1700

Data Index: 241643 (Open Web Text)

Max Activating Token Index: 358

Text #16

Max Range: 4.7238. Min Range: -4.7238

Max Act: 4.4026. Min Act: -0.1700

Data Index: 2145469 (Open Web Text)

Max Activating Token Index: 599

Text #17

Max Range: 4.7238. Min Range: -4.7238

Max Act: 4.4367. Min Act: -0.1700

Data Index: 8218625 (Open Web Text)

Max Activating Token Index: 98

Text #18

Max Range: 4.7238. Min Range: -4.7238

Max Act: 4.3967. Min Act: -0.1700

Data Index: 1862468 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 4.7238. Min Range: -4.7238

Max Act: 4.3751. Min Act: -0.1700

Data Index: 2043819 (Open Web Text)

Max Activating Token Index: 25