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

Dataset: Open Web Text

Neuron 488 in Layer 2

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: 1.6597. Min Range: -1.6597

Max Act: 1.6597. Min Act: -0.1700

Data Index: 3170599 (Open Web Text)

Max Activating Token Index: 639

Text #1

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.6437. Min Act: -0.1700

Data Index: 5030237 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.6446. Min Act: -0.1700

Data Index: 6743841 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.6453. Min Act: -0.1700

Data Index: 398359 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.6189. Min Act: -0.1700

Data Index: 8317385 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.6189. Min Act: -0.1700

Data Index: 2925319 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.6152. Min Act: -0.1700

Data Index: 3657814 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.6098. Min Act: -0.1698

Data Index: 764675 (Open Web Text)

Max Activating Token Index: 332

Text #8

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.6215. Min Act: -0.1700

Data Index: 6243603 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.6169. Min Act: -0.1700

Data Index: 6728166 (Open Web Text)

Max Activating Token Index: 575

Text #10

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.6022. Min Act: -0.1700

Data Index: 6669358 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.6075. Min Act: -0.1700

Data Index: 4853406 (Open Web Text)

Max Activating Token Index: 1004

Text #12

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.6045. Min Act: -0.1700

Data Index: 5216132 (Open Web Text)

Max Activating Token Index: 512

Text #13

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.5882. Min Act: -0.1700

Data Index: 2385273 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.5953. Min Act: -0.1700

Data Index: 3292840 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.5896. Min Act: -0.1700

Data Index: 2431302 (Open Web Text)

Max Activating Token Index: 630

Text #16

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.5996. Min Act: -0.1700

Data Index: 2385271 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.6050. Min Act: -0.1700

Data Index: 3298520 (Open Web Text)

Max Activating Token Index: 635

Text #18

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.6030. Min Act: -0.1700

Data Index: 4483617 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.5965. Min Act: -0.1699

Data Index: 2172411 (Open Web Text)

Max Activating Token Index: 737