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

Dataset: Open Web Text

Neuron 1729 in Layer 5

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: 4.2132. Min Range: -4.2132

Max Act: 4.2132. Min Act: -0.1700

Data Index: 7417577 (Open Web Text)

Max Activating Token Index: 43

Text #1

Max Range: 4.2132. Min Range: -4.2132

Max Act: 4.1704. Min Act: -0.1700

Data Index: 200655 (Open Web Text)

Max Activating Token Index: 193

Text #2

Max Range: 4.2132. Min Range: -4.2132

Max Act: 4.1500. Min Act: -0.1700

Data Index: 8718091 (Open Web Text)

Max Activating Token Index: 218

Text #3

Max Range: 4.2132. Min Range: -4.2132

Max Act: 4.1598. Min Act: -0.1700

Data Index: 6702845 (Open Web Text)

Max Activating Token Index: 365

Text #4

Max Range: 4.2132. Min Range: -4.2132

Max Act: 4.1341. Min Act: -0.1700

Data Index: 5136460 (Open Web Text)

Max Activating Token Index: 339

Text #5

Max Range: 4.2132. Min Range: -4.2132

Max Act: 4.1326. Min Act: -0.1700

Data Index: 8236068 (Open Web Text)

Max Activating Token Index: 188

Text #6

Max Range: 4.2132. Min Range: -4.2132

Max Act: 4.1320. Min Act: -0.1700

Data Index: 6104163 (Open Web Text)

Max Activating Token Index: 708

Text #7

Max Range: 4.2132. Min Range: -4.2132

Max Act: 4.0999. Min Act: -0.1700

Data Index: 7462552 (Open Web Text)

Max Activating Token Index: 302

Text #8

Max Range: 4.2132. Min Range: -4.2132

Max Act: 4.0959. Min Act: -0.1700

Data Index: 7496433 (Open Web Text)

Max Activating Token Index: 750

Text #9

Max Range: 4.2132. Min Range: -4.2132

Max Act: 4.0999. Min Act: -0.1700

Data Index: 8367216 (Open Web Text)

Max Activating Token Index: 61

Text #10

Max Range: 4.2132. Min Range: -4.2132

Max Act: 4.0788. Min Act: -0.1700

Data Index: 8282948 (Open Web Text)

Max Activating Token Index: 108

Text #11

Max Range: 4.2132. Min Range: -4.2132

Max Act: 4.0467. Min Act: -0.1700

Data Index: 4502995 (Open Web Text)

Max Activating Token Index: 58

Text #12

Max Range: 4.2132. Min Range: -4.2132

Max Act: 4.0183. Min Act: -0.1700

Data Index: 5558790 (Open Web Text)

Max Activating Token Index: 809

Text #13

Max Range: 4.2132. Min Range: -4.2132

Max Act: 4.0513. Min Act: -0.1700

Data Index: 3367650 (Open Web Text)

Max Activating Token Index: 221

Text #14

Max Range: 4.2132. Min Range: -4.2132

Max Act: 4.0205. Min Act: -0.1700

Data Index: 3725919 (Open Web Text)

Max Activating Token Index: 822

Text #15

Max Range: 4.2132. Min Range: -4.2132

Max Act: 4.0130. Min Act: -0.1700

Data Index: 5511013 (Open Web Text)

Max Activating Token Index: 323

Text #16

Max Range: 4.2132. Min Range: -4.2132

Max Act: 4.0493. Min Act: -0.1700

Data Index: 7597920 (Open Web Text)

Max Activating Token Index: 579

Text #17

Max Range: 4.2132. Min Range: -4.2132

Max Act: 4.0502. Min Act: -0.1700

Data Index: 259912 (Open Web Text)

Max Activating Token Index: 153

Text #18

Max Range: 4.2132. Min Range: -4.2132

Max Act: 4.0101. Min Act: -0.1700

Data Index: 39521 (Open Web Text)

Max Activating Token Index: 469

Text #19

Max Range: 4.2132. Min Range: -4.2132

Max Act: 4.0385. Min Act: -0.1700

Data Index: 7435136 (Open Web Text)

Max Activating Token Index: 80