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

Dataset: Open Web Text

Neuron 684 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: 3.2517. Min Range: -3.2517

Max Act: 3.2305. Min Act: -0.1700

Data Index: 423290 (Open Web Text)

Max Activating Token Index: 224

Text #1

Max Range: 3.2517. Min Range: -3.2517

Max Act: 3.2342. Min Act: -0.1700

Data Index: 1760435 (Open Web Text)

Max Activating Token Index: 575

Text #2

Max Range: 3.2517. Min Range: -3.2517

Max Act: 3.2517. Min Act: -0.1700

Data Index: 4380319 (Open Web Text)

Max Activating Token Index: 552

Text #3

Max Range: 3.2517. Min Range: -3.2517

Max Act: 3.1725. Min Act: -0.1700

Data Index: 5148123 (Open Web Text)

Max Activating Token Index: 476

Text #4

Max Range: 3.2517. Min Range: -3.2517

Max Act: 3.1963. Min Act: -0.1700

Data Index: 7373099 (Open Web Text)

Max Activating Token Index: 992

Text #5

Max Range: 3.2517. Min Range: -3.2517

Max Act: 3.1730. Min Act: -0.1700

Data Index: 388302 (Open Web Text)

Max Activating Token Index: 656

Text #6

Max Range: 3.2517. Min Range: -3.2517

Max Act: 3.1643. Min Act: -0.1700

Data Index: 4546697 (Open Web Text)

Max Activating Token Index: 10

Text #7

Max Range: 3.2517. Min Range: -3.2517

Max Act: 3.1798. Min Act: -0.1700

Data Index: 4775988 (Open Web Text)

Max Activating Token Index: 252

Text #8

Max Range: 3.2517. Min Range: -3.2517

Max Act: 3.1470. Min Act: -0.1700

Data Index: 5565229 (Open Web Text)

Max Activating Token Index: 718

Text #9

Max Range: 3.2517. Min Range: -3.2517

Max Act: 3.1478. Min Act: -0.1700

Data Index: 6631443 (Open Web Text)

Max Activating Token Index: 33

Text #10

Max Range: 3.2517. Min Range: -3.2517

Max Act: 3.1374. Min Act: -0.1700

Data Index: 1041431 (Open Web Text)

Max Activating Token Index: 13

Text #11

Max Range: 3.2517. Min Range: -3.2517

Max Act: 3.1164. Min Act: -0.1700

Data Index: 5576523 (Open Web Text)

Max Activating Token Index: 392

Text #12

Max Range: 3.2517. Min Range: -3.2517

Max Act: 3.1117. Min Act: -0.1700

Data Index: 1204336 (Open Web Text)

Max Activating Token Index: 935

Text #13

Max Range: 3.2517. Min Range: -3.2517

Max Act: 3.1013. Min Act: -0.1700

Data Index: 139185 (Open Web Text)

Max Activating Token Index: 895

Text #14

Max Range: 3.2517. Min Range: -3.2517

Max Act: 3.1196. Min Act: -0.1700

Data Index: 6395796 (Open Web Text)

Max Activating Token Index: 353

Text #15

Max Range: 3.2517. Min Range: -3.2517

Max Act: 3.1182. Min Act: -0.1700

Data Index: 3078697 (Open Web Text)

Max Activating Token Index: 989

Text #16

Max Range: 3.2517. Min Range: -3.2517

Max Act: 3.0871. Min Act: -0.1700

Data Index: 5345183 (Open Web Text)

Max Activating Token Index: 194

Text #17

Max Range: 3.2517. Min Range: -3.2517

Max Act: 3.0834. Min Act: -0.1700

Data Index: 4215511 (Open Web Text)

Max Activating Token Index: 251

Text #18

Max Range: 3.2517. Min Range: -3.2517

Max Act: 3.1001. Min Act: -0.1700

Data Index: 3501598 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 3.2517. Min Range: -3.2517

Max Act: 3.1089. Min Act: -0.1700

Data Index: 1102065 (Open Web Text)

Max Activating Token Index: 62