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

Dataset: Open Web Text

Neuron 69 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: 1.6568. Min Range: -1.6568

Max Act: 1.6568. Min Act: -0.1700

Data Index: 6223913 (Open Web Text)

Max Activating Token Index: 34

Text #1

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.6450. Min Act: -0.1700

Data Index: 5999661 (Open Web Text)

Max Activating Token Index: 251

Text #2

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.6297. Min Act: -0.1700

Data Index: 296704 (Open Web Text)

Max Activating Token Index: 233

Text #3

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.6437. Min Act: -0.1700

Data Index: 4384926 (Open Web Text)

Max Activating Token Index: 288

Text #4

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.6335. Min Act: -0.1700

Data Index: 3723592 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.6234. Min Act: -0.1700

Data Index: 5262043 (Open Web Text)

Max Activating Token Index: 124

Text #6

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.6247. Min Act: -0.1700

Data Index: 3236298 (Open Web Text)

Max Activating Token Index: 846

Text #7

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.6153. Min Act: -0.1699

Data Index: 8051834 (Open Web Text)

Max Activating Token Index: 384

Text #8

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.6101. Min Act: -0.1700

Data Index: 2717680 (Open Web Text)

Max Activating Token Index: 261

Text #9

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.6200. Min Act: -0.1700

Data Index: 2336639 (Open Web Text)

Max Activating Token Index: 25

Text #10

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.6081. Min Act: -0.1700

Data Index: 8329713 (Open Web Text)

Max Activating Token Index: 243

Text #11

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.6068. Min Act: -0.1700

Data Index: 4139278 (Open Web Text)

Max Activating Token Index: 187

Text #12

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.6009. Min Act: -0.1700

Data Index: 2813046 (Open Web Text)

Max Activating Token Index: 696

Text #13

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.6005. Min Act: -0.1700

Data Index: 7782829 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.5956. Min Act: -0.1700

Data Index: 5669490 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.6002. Min Act: -0.1700

Data Index: 1827804 (Open Web Text)

Max Activating Token Index: 22

Text #16

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.5760. Min Act: -0.1700

Data Index: 7457927 (Open Web Text)

Max Activating Token Index: 373

Text #17

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.5896. Min Act: -0.1700

Data Index: 2298031 (Open Web Text)

Max Activating Token Index: 28

Text #18

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.5981. Min Act: -0.1700

Data Index: 4120316 (Open Web Text)

Max Activating Token Index: 802

Text #19

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.5785. Min Act: -0.1700

Data Index: 405150 (Open Web Text)

Max Activating Token Index: 372