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

Dataset: Open Web Text

Neuron 163 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: 4.5173. Min Range: -4.5173

Max Act: 4.5173. Min Act: -0.1700

Data Index: 951324 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 4.5173. Min Range: -4.5173

Max Act: 4.4941. Min Act: -0.1700

Data Index: 4923100 (Open Web Text)

Max Activating Token Index: 52

Text #2

Max Range: 4.5173. Min Range: -4.5173

Max Act: 4.3888. Min Act: -0.1700

Data Index: 4199867 (Open Web Text)

Max Activating Token Index: 275

Text #3

Max Range: 4.5173. Min Range: -4.5173

Max Act: 4.3891. Min Act: -0.1700

Data Index: 6766157 (Open Web Text)

Max Activating Token Index: 258

Text #4

Max Range: 4.5173. Min Range: -4.5173

Max Act: 4.3730. Min Act: -0.1700

Data Index: 7692111 (Open Web Text)

Max Activating Token Index: 57

Text #5

Max Range: 4.5173. Min Range: -4.5173

Max Act: 4.3485. Min Act: -0.1700

Data Index: 2460356 (Open Web Text)

Max Activating Token Index: 292

Text #6

Max Range: 4.5173. Min Range: -4.5173

Max Act: 4.3378. Min Act: -0.1700

Data Index: 4714468 (Open Web Text)

Max Activating Token Index: 220

Text #7

Max Range: 4.5173. Min Range: -4.5173

Max Act: 4.3459. Min Act: -0.1700

Data Index: 6713030 (Open Web Text)

Max Activating Token Index: 337

Text #8

Max Range: 4.5173. Min Range: -4.5173

Max Act: 4.3535. Min Act: -0.1700

Data Index: 7302051 (Open Web Text)

Max Activating Token Index: 333

Text #9

Max Range: 4.5173. Min Range: -4.5173

Max Act: 4.2989. Min Act: -0.1700

Data Index: 7750080 (Open Web Text)

Max Activating Token Index: 599

Text #10

Max Range: 4.5173. Min Range: -4.5173

Max Act: 4.3260. Min Act: -0.1700

Data Index: 5838430 (Open Web Text)

Max Activating Token Index: 587

Text #11

Max Range: 4.5173. Min Range: -4.5173

Max Act: 4.2660. Min Act: -0.1700

Data Index: 4033566 (Open Web Text)

Max Activating Token Index: 32

Text #12

Max Range: 4.5173. Min Range: -4.5173

Max Act: 4.3136. Min Act: -0.1700

Data Index: 2646423 (Open Web Text)

Max Activating Token Index: 226

Text #13

Max Range: 4.5173. Min Range: -4.5173

Max Act: 4.3304. Min Act: -0.1700

Data Index: 2477884 (Open Web Text)

Max Activating Token Index: 904

Text #14

Max Range: 4.5173. Min Range: -4.5173

Max Act: 4.2693. Min Act: -0.1700

Data Index: 2601410 (Open Web Text)

Max Activating Token Index: 411

Text #15

Max Range: 4.5173. Min Range: -4.5173

Max Act: 4.2784. Min Act: -0.1700

Data Index: 3540582 (Open Web Text)

Max Activating Token Index: 82

Text #16

Max Range: 4.5173. Min Range: -4.5173

Max Act: 4.2780. Min Act: -0.1700

Data Index: 8771453 (Open Web Text)

Max Activating Token Index: 854

Text #17

Max Range: 4.5173. Min Range: -4.5173

Max Act: 4.2634. Min Act: -0.1700

Data Index: 51507 (Open Web Text)

Max Activating Token Index: 520

Text #18

Max Range: 4.5173. Min Range: -4.5173

Max Act: 4.2382. Min Act: -0.1700

Data Index: 7132756 (Open Web Text)

Max Activating Token Index: 653

Text #19

Max Range: 4.5173. Min Range: -4.5173

Max Act: 4.2091. Min Act: -0.1700

Data Index: 1594255 (Open Web Text)

Max Activating Token Index: 880