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

Dataset: Open Web Text

Neuron 1498 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: 1.7052. Min Range: -1.7052

Max Act: 1.7052. Min Act: -0.1684

Data Index: 99206 (Open Web Text)

Max Activating Token Index: 212

Text #1

Max Range: 1.7052. Min Range: -1.7052

Max Act: 1.6567. Min Act: -0.1697

Data Index: 5512237 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 1.7052. Min Range: -1.7052

Max Act: 1.6448. Min Act: -0.1698

Data Index: 4496019 (Open Web Text)

Max Activating Token Index: 433

Text #3

Max Range: 1.7052. Min Range: -1.7052

Max Act: 1.6394. Min Act: -0.1699

Data Index: 8433451 (Open Web Text)

Max Activating Token Index: 560

Text #4

Max Range: 1.7052. Min Range: -1.7052

Max Act: 1.6431. Min Act: -0.1700

Data Index: 7717815 (Open Web Text)

Max Activating Token Index: 937

Text #5

Max Range: 1.7052. Min Range: -1.7052

Max Act: 1.6303. Min Act: -0.1700

Data Index: 3418815 (Open Web Text)

Max Activating Token Index: 638

Text #6

Max Range: 1.7052. Min Range: -1.7052

Max Act: 1.6342. Min Act: -0.1687

Data Index: 2908723 (Open Web Text)

Max Activating Token Index: 340

Text #7

Max Range: 1.7052. Min Range: -1.7052

Max Act: 1.6167. Min Act: -0.1700

Data Index: 2818292 (Open Web Text)

Max Activating Token Index: 551

Text #8

Max Range: 1.7052. Min Range: -1.7052

Max Act: 1.6170. Min Act: -0.1700

Data Index: 8535232 (Open Web Text)

Max Activating Token Index: 42

Text #9

Max Range: 1.7052. Min Range: -1.7052

Max Act: 1.6261. Min Act: -0.1693

Data Index: 1004544 (Open Web Text)

Max Activating Token Index: 563

Text #10

Max Range: 1.7052. Min Range: -1.7052

Max Act: 1.6215. Min Act: -0.1698

Data Index: 7161584 (Open Web Text)

Max Activating Token Index: 668

Text #11

Max Range: 1.7052. Min Range: -1.7052

Max Act: 1.6204. Min Act: -0.1700

Data Index: 129833 (Open Web Text)

Max Activating Token Index: 145

Text #12

Max Range: 1.7052. Min Range: -1.7052

Max Act: 1.6306. Min Act: -0.1700

Data Index: 1763687 (Open Web Text)

Max Activating Token Index: 521

Text #13

Max Range: 1.7052. Min Range: -1.7052

Max Act: 1.6118. Min Act: -0.1671

Data Index: 3762077 (Open Web Text)

Max Activating Token Index: 251

Text #14

Max Range: 1.7052. Min Range: -1.7052

Max Act: 1.6035. Min Act: -0.1700

Data Index: 2601813 (Open Web Text)

Max Activating Token Index: 953

Text #15

Max Range: 1.7052. Min Range: -1.7052

Max Act: 1.6034. Min Act: -0.1698

Data Index: 2146443 (Open Web Text)

Max Activating Token Index: 254

Text #16

Max Range: 1.7052. Min Range: -1.7052

Max Act: 1.6008. Min Act: -0.1700

Data Index: 2571101 (Open Web Text)

Max Activating Token Index: 432

Text #17

Max Range: 1.7052. Min Range: -1.7052

Max Act: 1.5985. Min Act: -0.1699

Data Index: 1270982 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 1.7052. Min Range: -1.7052

Max Act: 1.5992. Min Act: -0.1700

Data Index: 1093184 (Open Web Text)

Max Activating Token Index: 407

Text #19

Max Range: 1.7052. Min Range: -1.7052

Max Act: 1.5985. Min Act: -0.1694

Data Index: 319852 (Open Web Text)

Max Activating Token Index: 365