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

Dataset: Open Web Text

Neuron 103 in Layer 5

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: 3.4634. Min Range: -3.4634

Max Act: 3.4634. Min Act: -0.1700

Data Index: 8705629 (Open Web Text)

Max Activating Token Index: 313

Text #1

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.3365. Min Act: -0.1700

Data Index: 6190244 (Open Web Text)

Max Activating Token Index: 285

Text #2

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.3201. Min Act: -0.1700

Data Index: 7329642 (Open Web Text)

Max Activating Token Index: 455

Text #3

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.3188. Min Act: -0.1700

Data Index: 2497047 (Open Web Text)

Max Activating Token Index: 188

Text #4

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.2628. Min Act: -0.1700

Data Index: 1109213 (Open Web Text)

Max Activating Token Index: 947

Text #5

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.2515. Min Act: -0.1700

Data Index: 6602708 (Open Web Text)

Max Activating Token Index: 254

Text #6

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.2491. Min Act: -0.1700

Data Index: 2691680 (Open Web Text)

Max Activating Token Index: 144

Text #7

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.2403. Min Act: -0.1700

Data Index: 5271155 (Open Web Text)

Max Activating Token Index: 216

Text #8

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.2362. Min Act: -0.1700

Data Index: 8457906 (Open Web Text)

Max Activating Token Index: 468

Text #9

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.2500. Min Act: -0.1700

Data Index: 2490738 (Open Web Text)

Max Activating Token Index: 237

Text #10

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.2164. Min Act: -0.1700

Data Index: 1842545 (Open Web Text)

Max Activating Token Index: 352

Text #11

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.2385. Min Act: -0.1700

Data Index: 8071891 (Open Web Text)

Max Activating Token Index: 707

Text #12

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.2263. Min Act: -0.1700

Data Index: 6667018 (Open Web Text)

Max Activating Token Index: 416

Text #13

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.2260. Min Act: -0.1700

Data Index: 4768085 (Open Web Text)

Max Activating Token Index: 71

Text #14

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.2408. Min Act: -0.1700

Data Index: 1088368 (Open Web Text)

Max Activating Token Index: 974

Text #15

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.2211. Min Act: -0.1700

Data Index: 3293378 (Open Web Text)

Max Activating Token Index: 409

Text #16

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.2142. Min Act: -0.1700

Data Index: 1257410 (Open Web Text)

Max Activating Token Index: 472

Text #17

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.2161. Min Act: -0.1700

Data Index: 7139954 (Open Web Text)

Max Activating Token Index: 618

Text #18

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.2028. Min Act: -0.1700

Data Index: 4530124 (Open Web Text)

Max Activating Token Index: 518

Text #19

Max Range: 3.4634. Min Range: -3.4634

Max Act: 3.1861. Min Act: -0.1700

Data Index: 7408864 (Open Web Text)

Max Activating Token Index: 625