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

Dataset: Open Web Text

Neuron 1632 in Layer 4

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: 4.5443. Min Range: -4.5443

Max Act: 4.5443. Min Act: -0.1700

Data Index: 7164661 (Open Web Text)

Max Activating Token Index: 939

Text #1

Max Range: 4.5443. Min Range: -4.5443

Max Act: 4.4255. Min Act: -0.1700

Data Index: 3304514 (Open Web Text)

Max Activating Token Index: 780

Text #2

Max Range: 4.5443. Min Range: -4.5443

Max Act: 4.4279. Min Act: -0.1700

Data Index: 4178339 (Open Web Text)

Max Activating Token Index: 436

Text #3

Max Range: 4.5443. Min Range: -4.5443

Max Act: 4.4065. Min Act: -0.1700

Data Index: 6607042 (Open Web Text)

Max Activating Token Index: 583

Text #4

Max Range: 4.5443. Min Range: -4.5443

Max Act: 4.3367. Min Act: -0.1700

Data Index: 4883607 (Open Web Text)

Max Activating Token Index: 13

Text #5

Max Range: 4.5443. Min Range: -4.5443

Max Act: 4.2944. Min Act: -0.1700

Data Index: 1030731 (Open Web Text)

Max Activating Token Index: 128

Text #6

Max Range: 4.5443. Min Range: -4.5443

Max Act: 4.3523. Min Act: -0.1700

Data Index: 1199366 (Open Web Text)

Max Activating Token Index: 929

Text #7

Max Range: 4.5443. Min Range: -4.5443

Max Act: 4.2126. Min Act: -0.1700

Data Index: 5993911 (Open Web Text)

Max Activating Token Index: 793

Text #8

Max Range: 4.5443. Min Range: -4.5443

Max Act: 4.2748. Min Act: -0.1700

Data Index: 7486943 (Open Web Text)

Max Activating Token Index: 27

Text #9

Max Range: 4.5443. Min Range: -4.5443

Max Act: 4.2700. Min Act: -0.1700

Data Index: 6539700 (Open Web Text)

Max Activating Token Index: 194

Text #10

Max Range: 4.5443. Min Range: -4.5443

Max Act: 4.2831. Min Act: -0.1700

Data Index: 4722791 (Open Web Text)

Max Activating Token Index: 16

Text #11

Max Range: 4.5443. Min Range: -4.5443

Max Act: 4.2834. Min Act: -0.1700

Data Index: 1695100 (Open Web Text)

Max Activating Token Index: 1013

Text #12

Max Range: 4.5443. Min Range: -4.5443

Max Act: 4.2306. Min Act: -0.1700

Data Index: 2862291 (Open Web Text)

Max Activating Token Index: 455

Text #13

Max Range: 4.5443. Min Range: -4.5443

Max Act: 4.2175. Min Act: -0.1700

Data Index: 1819097 (Open Web Text)

Max Activating Token Index: 596

Text #14

Max Range: 4.5443. Min Range: -4.5443

Max Act: 4.2347. Min Act: -0.1700

Data Index: 8500821 (Open Web Text)

Max Activating Token Index: 153

Text #15

Max Range: 4.5443. Min Range: -4.5443

Max Act: 4.2271. Min Act: -0.1700

Data Index: 169241 (Open Web Text)

Max Activating Token Index: 227

Text #16

Max Range: 4.5443. Min Range: -4.5443

Max Act: 4.2530. Min Act: -0.1700

Data Index: 8797793 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.5443. Min Range: -4.5443

Max Act: 4.2027. Min Act: -0.1700

Data Index: 5500281 (Open Web Text)

Max Activating Token Index: 233

Text #18

Max Range: 4.5443. Min Range: -4.5443

Max Act: 4.1856. Min Act: -0.1700

Data Index: 693872 (Open Web Text)

Max Activating Token Index: 396

Text #19

Max Range: 4.5443. Min Range: -4.5443

Max Act: 4.2128. Min Act: -0.1700

Data Index: 214102 (Open Web Text)

Max Activating Token Index: 8