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

Dataset: Open Web Text

Neuron 238 in Layer 2

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: 3.2784. Min Range: -3.2784

Max Act: 3.2784. Min Act: -0.1700

Data Index: 936034 (Open Web Text)

Max Activating Token Index: 822

Text #1

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.2752. Min Act: -0.1700

Data Index: 6340443 (Open Web Text)

Max Activating Token Index: 218

Text #2

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.2714. Min Act: -0.1700

Data Index: 8486861 (Open Web Text)

Max Activating Token Index: 485

Text #3

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.2205. Min Act: -0.1700

Data Index: 8662787 (Open Web Text)

Max Activating Token Index: 407

Text #4

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.2445. Min Act: -0.1700

Data Index: 1662485 (Open Web Text)

Max Activating Token Index: 380

Text #5

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.2202. Min Act: -0.1700

Data Index: 6393413 (Open Web Text)

Max Activating Token Index: 860

Text #6

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.1995. Min Act: -0.1700

Data Index: 1264634 (Open Web Text)

Max Activating Token Index: 424

Text #7

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.1876. Min Act: -0.1700

Data Index: 5431157 (Open Web Text)

Max Activating Token Index: 524

Text #8

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.1641. Min Act: -0.1700

Data Index: 279363 (Open Web Text)

Max Activating Token Index: 245

Text #9

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.1713. Min Act: -0.1700

Data Index: 4335907 (Open Web Text)

Max Activating Token Index: 388

Text #10

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.1586. Min Act: -0.1700

Data Index: 4881391 (Open Web Text)

Max Activating Token Index: 331

Text #11

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.1667. Min Act: -0.1700

Data Index: 2110478 (Open Web Text)

Max Activating Token Index: 218

Text #12

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.1688. Min Act: -0.1700

Data Index: 1862245 (Open Web Text)

Max Activating Token Index: 237

Text #13

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.1486. Min Act: -0.1700

Data Index: 8350834 (Open Web Text)

Max Activating Token Index: 399

Text #14

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.1382. Min Act: -0.1700

Data Index: 8285548 (Open Web Text)

Max Activating Token Index: 137

Text #15

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.1388. Min Act: -0.1700

Data Index: 7099541 (Open Web Text)

Max Activating Token Index: 714

Text #16

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.1548. Min Act: -0.1700

Data Index: 41855 (Open Web Text)

Max Activating Token Index: 284

Text #17

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.1363. Min Act: -0.1700

Data Index: 2946777 (Open Web Text)

Max Activating Token Index: 227

Text #18

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.1167. Min Act: -0.1700

Data Index: 4849638 (Open Web Text)

Max Activating Token Index: 226

Text #19

Max Range: 3.2784. Min Range: -3.2784

Max Act: 3.0966. Min Act: -0.1700

Data Index: 6913834 (Open Web Text)

Max Activating Token Index: 621