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

Dataset: Open Web Text

Neuron 2088 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: 1.4332. Min Range: -1.4332

Max Act: 1.4327. Min Act: -0.1003

Data Index: 8657098 (Open Web Text)

Max Activating Token Index: 616

Text #1

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.4332. Min Act: -0.0557

Data Index: 1954600 (Open Web Text)

Max Activating Token Index: 180

Text #2

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.4253. Min Act: -0.0467

Data Index: 1416346 (Open Web Text)

Max Activating Token Index: 72

Text #3

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.4174. Min Act: -0.1483

Data Index: 5565270 (Open Web Text)

Max Activating Token Index: 1018

Text #4

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.4182. Min Act: -0.0536

Data Index: 3235574 (Open Web Text)

Max Activating Token Index: 583

Text #5

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.4217. Min Act: -0.0437

Data Index: 7991053 (Open Web Text)

Max Activating Token Index: 614

Text #6

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.4064. Min Act: -0.1059

Data Index: 7690209 (Open Web Text)

Max Activating Token Index: 668

Text #7

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.4220. Min Act: -0.1300

Data Index: 5771404 (Open Web Text)

Max Activating Token Index: 664

Text #8

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.4091. Min Act: -0.0784

Data Index: 6092019 (Open Web Text)

Max Activating Token Index: 671

Text #9

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.3949. Min Act: -0.1558

Data Index: 4429952 (Open Web Text)

Max Activating Token Index: 1019

Text #10

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.3966. Min Act: -0.0425

Data Index: 4245960 (Open Web Text)

Max Activating Token Index: 659

Text #11

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.4000. Min Act: -0.1386

Data Index: 3620247 (Open Web Text)

Max Activating Token Index: 1000

Text #12

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.3948. Min Act: -0.0699

Data Index: 5699746 (Open Web Text)

Max Activating Token Index: 350

Text #13

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.3845. Min Act: -0.0940

Data Index: 682671 (Open Web Text)

Max Activating Token Index: 640

Text #14

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.3905. Min Act: -0.0316

Data Index: 561686 (Open Web Text)

Max Activating Token Index: 1012

Text #15

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.3911. Min Act: -0.0973

Data Index: 6387188 (Open Web Text)

Max Activating Token Index: 609

Text #16

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.3883. Min Act: -0.1136

Data Index: 1388924 (Open Web Text)

Max Activating Token Index: 647

Text #17

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.3853. Min Act: -0.1089

Data Index: 6551986 (Open Web Text)

Max Activating Token Index: 628

Text #18

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.3912. Min Act: -0.1114

Data Index: 7349246 (Open Web Text)

Max Activating Token Index: 682

Text #19

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.3876. Min Act: -0.1413

Data Index: 4242741 (Open Web Text)

Max Activating Token Index: 1022