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

Dataset: Open Web Text

Neuron 457 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: 1.9256. Min Range: -1.9256

Max Act: 1.9256. Min Act: -0.1700

Data Index: 2205186 (Open Web Text)

Max Activating Token Index: 67

Text #1

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8735. Min Act: -0.1700

Data Index: 1277972 (Open Web Text)

Max Activating Token Index: 74

Text #2

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8705. Min Act: -0.1690

Data Index: 2032384 (Open Web Text)

Max Activating Token Index: 294

Text #3

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8695. Min Act: -0.1700

Data Index: 2480097 (Open Web Text)

Max Activating Token Index: 720

Text #4

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8678. Min Act: -0.1700

Data Index: 15520 (Open Web Text)

Max Activating Token Index: 416

Text #5

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8616. Min Act: -0.1700

Data Index: 3040888 (Open Web Text)

Max Activating Token Index: 143

Text #6

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8596. Min Act: -0.1700

Data Index: 7854445 (Open Web Text)

Max Activating Token Index: 74

Text #7

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8554. Min Act: -0.1699

Data Index: 6091894 (Open Web Text)

Max Activating Token Index: 164

Text #8

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8530. Min Act: -0.1700

Data Index: 4042189 (Open Web Text)

Max Activating Token Index: 121

Text #9

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8446. Min Act: -0.1700

Data Index: 4553723 (Open Web Text)

Max Activating Token Index: 1006

Text #10

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8342. Min Act: -0.1700

Data Index: 1969306 (Open Web Text)

Max Activating Token Index: 362

Text #11

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8446. Min Act: -0.1700

Data Index: 5108434 (Open Web Text)

Max Activating Token Index: 226

Text #12

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8401. Min Act: -0.1700

Data Index: 4457340 (Open Web Text)

Max Activating Token Index: 321

Text #13

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8229. Min Act: -0.1696

Data Index: 4163460 (Open Web Text)

Max Activating Token Index: 103

Text #14

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8250. Min Act: -0.1700

Data Index: 2086583 (Open Web Text)

Max Activating Token Index: 232

Text #15

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8232. Min Act: -0.1700

Data Index: 3804671 (Open Web Text)

Max Activating Token Index: 301

Text #16

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8220. Min Act: -0.1700

Data Index: 1969305 (Open Web Text)

Max Activating Token Index: 484

Text #17

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8178. Min Act: -0.1700

Data Index: 3006207 (Open Web Text)

Max Activating Token Index: 403

Text #18

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8161. Min Act: -0.1700

Data Index: 7727870 (Open Web Text)

Max Activating Token Index: 450

Text #19

Max Range: 1.9256. Min Range: -1.9256

Max Act: 1.8129. Min Act: -0.1700

Data Index: 6067782 (Open Web Text)

Max Activating Token Index: 314