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

Dataset: Open Web Text

Neuron 1372 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: 1.2336. Min Range: -1.2336

Max Act: 1.2334. Min Act: -0.1700

Data Index: 8452848 (Open Web Text)

Max Activating Token Index: 581

Text #1

Max Range: 1.2336. Min Range: -1.2336

Max Act: 1.2242. Min Act: -0.1700

Data Index: 2294813 (Open Web Text)

Max Activating Token Index: 505

Text #2

Max Range: 1.2336. Min Range: -1.2336

Max Act: 1.2336. Min Act: -0.1698

Data Index: 5039603 (Open Web Text)

Max Activating Token Index: 116

Text #3

Max Range: 1.2336. Min Range: -1.2336

Max Act: 1.2164. Min Act: -0.1700

Data Index: 1833479 (Open Web Text)

Max Activating Token Index: 756

Text #4

Max Range: 1.2336. Min Range: -1.2336

Max Act: 1.2212. Min Act: -0.1700

Data Index: 1410102 (Open Web Text)

Max Activating Token Index: 275

Text #5

Max Range: 1.2336. Min Range: -1.2336

Max Act: 1.2092. Min Act: -0.1700

Data Index: 2980607 (Open Web Text)

Max Activating Token Index: 177

Text #6

Max Range: 1.2336. Min Range: -1.2336

Max Act: 1.2099. Min Act: -0.1700

Data Index: 448623 (Open Web Text)

Max Activating Token Index: 542

Text #7

Max Range: 1.2336. Min Range: -1.2336

Max Act: 1.2053. Min Act: -0.1690

Data Index: 4103218 (Open Web Text)

Max Activating Token Index: 245

Text #8

Max Range: 1.2336. Min Range: -1.2336

Max Act: 1.2033. Min Act: -0.1699

Data Index: 2389547 (Open Web Text)

Max Activating Token Index: 72

Text #9

Max Range: 1.2336. Min Range: -1.2336

Max Act: 1.2026. Min Act: -0.1700

Data Index: 6138740 (Open Web Text)

Max Activating Token Index: 860

Text #10

Max Range: 1.2336. Min Range: -1.2336

Max Act: 1.1950. Min Act: -0.1700

Data Index: 4102549 (Open Web Text)

Max Activating Token Index: 129

Text #11

Max Range: 1.2336. Min Range: -1.2336

Max Act: 1.2023. Min Act: -0.1699

Data Index: 7737443 (Open Web Text)

Max Activating Token Index: 264

Text #12

Max Range: 1.2336. Min Range: -1.2336

Max Act: 1.2019. Min Act: -0.1700

Data Index: 3668291 (Open Web Text)

Max Activating Token Index: 365

Text #13

Max Range: 1.2336. Min Range: -1.2336

Max Act: 1.1844. Min Act: -0.1700

Data Index: 6415323 (Open Web Text)

Max Activating Token Index: 662

Text #14

Max Range: 1.2336. Min Range: -1.2336

Max Act: 1.1875. Min Act: -0.1700

Data Index: 692228 (Open Web Text)

Max Activating Token Index: 168

Text #15

Max Range: 1.2336. Min Range: -1.2336

Max Act: 1.1881. Min Act: -0.1700

Data Index: 6138736 (Open Web Text)

Max Activating Token Index: 372

Text #16

Max Range: 1.2336. Min Range: -1.2336

Max Act: 1.1811. Min Act: -0.1700

Data Index: 937089 (Open Web Text)

Max Activating Token Index: 157

Text #17

Max Range: 1.2336. Min Range: -1.2336

Max Act: 1.1874. Min Act: -0.1696

Data Index: 5955382 (Open Web Text)

Max Activating Token Index: 546

Text #18

Max Range: 1.2336. Min Range: -1.2336

Max Act: 1.1890. Min Act: -0.1699

Data Index: 4017921 (Open Web Text)

Max Activating Token Index: 611

Text #19

Max Range: 1.2336. Min Range: -1.2336

Max Act: 1.1804. Min Act: -0.1699

Data Index: 3611401 (Open Web Text)

Max Activating Token Index: 50