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

Dataset: Open Web Text

Neuron 1294 in Layer 0

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: 7.9386. Min Range: -7.9386

Max Act: 7.9386. Min Act: -0.1700

Data Index: 3217488 (Open Web Text)

Max Activating Token Index: 11

Text #1

Max Range: 7.9386. Min Range: -7.9386

Max Act: 7.5574. Min Act: -0.1700

Data Index: 812396 (Open Web Text)

Max Activating Token Index: 653

Text #2

Max Range: 7.9386. Min Range: -7.9386

Max Act: 7.5125. Min Act: -0.1700

Data Index: 294679 (Open Web Text)

Max Activating Token Index: 16

Text #3

Max Range: 7.9386. Min Range: -7.9386

Max Act: 7.5393. Min Act: -0.1700

Data Index: 6300914 (Open Web Text)

Max Activating Token Index: 631

Text #4

Max Range: 7.9386. Min Range: -7.9386

Max Act: 7.3878. Min Act: -0.1700

Data Index: 666907 (Open Web Text)

Max Activating Token Index: 25

Text #5

Max Range: 7.9386. Min Range: -7.9386

Max Act: 7.4139. Min Act: -0.1700

Data Index: 2477646 (Open Web Text)

Max Activating Token Index: 15

Text #6

Max Range: 7.9386. Min Range: -7.9386

Max Act: 7.3367. Min Act: -0.1700

Data Index: 2192188 (Open Web Text)

Max Activating Token Index: 40

Text #7

Max Range: 7.9386. Min Range: -7.9386

Max Act: 7.2968. Min Act: -0.1696

Data Index: 4848259 (Open Web Text)

Max Activating Token Index: 347

Text #8

Max Range: 7.9386. Min Range: -7.9386

Max Act: 7.2906. Min Act: -0.1700

Data Index: 1414599 (Open Web Text)

Max Activating Token Index: 21

Text #9

Max Range: 7.9386. Min Range: -7.9386

Max Act: 7.2397. Min Act: -0.1700

Data Index: 4278549 (Open Web Text)

Max Activating Token Index: 61

Text #10

Max Range: 7.9386. Min Range: -7.9386

Max Act: 7.2704. Min Act: -0.1700

Data Index: 436294 (Open Web Text)

Max Activating Token Index: 278

Text #11

Max Range: 7.9386. Min Range: -7.9386

Max Act: 7.3086. Min Act: -0.1700

Data Index: 7918395 (Open Web Text)

Max Activating Token Index: 27

Text #12

Max Range: 7.9386. Min Range: -7.9386

Max Act: 7.1913. Min Act: -0.1700

Data Index: 4138475 (Open Web Text)

Max Activating Token Index: 319

Text #13

Max Range: 7.9386. Min Range: -7.9386

Max Act: 7.2267. Min Act: -0.1699

Data Index: 4815125 (Open Web Text)

Max Activating Token Index: 171

Text #14

Max Range: 7.9386. Min Range: -7.9386

Max Act: 7.2009. Min Act: -0.1700

Data Index: 334285 (Open Web Text)

Max Activating Token Index: 287

Text #15

Max Range: 7.9386. Min Range: -7.9386

Max Act: 7.2216. Min Act: -0.1691

Data Index: 6367181 (Open Web Text)

Max Activating Token Index: 258

Text #16

Max Range: 7.9386. Min Range: -7.9386

Max Act: 7.2254. Min Act: -0.1700

Data Index: 5380443 (Open Web Text)

Max Activating Token Index: 241

Text #17

Max Range: 7.9386. Min Range: -7.9386

Max Act: 7.2179. Min Act: -0.1700

Data Index: 6787518 (Open Web Text)

Max Activating Token Index: 19

Text #18

Max Range: 7.9386. Min Range: -7.9386

Max Act: 7.1954. Min Act: -0.1700

Data Index: 3193612 (Open Web Text)

Max Activating Token Index: 52

Text #19

Max Range: 7.9386. Min Range: -7.9386

Max Act: 7.2012. Min Act: -0.1700

Data Index: 2456016 (Open Web Text)

Max Activating Token Index: 166