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

Dataset: Open Web Text

Neuron 1675 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: 2.4241. Min Range: -2.4241

Max Act: 2.4241. Min Act: -0.1693

Data Index: 5955270 (Open Web Text)

Max Activating Token Index: 74

Text #1

Max Range: 2.4241. Min Range: -2.4241

Max Act: 2.2964. Min Act: -0.1700

Data Index: 8134769 (Open Web Text)

Max Activating Token Index: 217

Text #2

Max Range: 2.4241. Min Range: -2.4241

Max Act: 2.2978. Min Act: -0.1700

Data Index: 3792673 (Open Web Text)

Max Activating Token Index: 149

Text #3

Max Range: 2.4241. Min Range: -2.4241

Max Act: 2.3049. Min Act: -0.1700

Data Index: 4220132 (Open Web Text)

Max Activating Token Index: 12

Text #4

Max Range: 2.4241. Min Range: -2.4241

Max Act: 2.2983. Min Act: -0.1700

Data Index: 6024127 (Open Web Text)

Max Activating Token Index: 147

Text #5

Max Range: 2.4241. Min Range: -2.4241

Max Act: 2.2901. Min Act: -0.1700

Data Index: 4859364 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 2.4241. Min Range: -2.4241

Max Act: 2.3019. Min Act: -0.1654

Data Index: 5236066 (Open Web Text)

Max Activating Token Index: 386

Text #7

Max Range: 2.4241. Min Range: -2.4241

Max Act: 2.2851. Min Act: -0.1684

Data Index: 2131707 (Open Web Text)

Max Activating Token Index: 26

Text #8

Max Range: 2.4241. Min Range: -2.4241

Max Act: 2.2874. Min Act: -0.1586

Data Index: 4280265 (Open Web Text)

Max Activating Token Index: 333

Text #9

Max Range: 2.4241. Min Range: -2.4241

Max Act: 2.2894. Min Act: -0.1700

Data Index: 4297415 (Open Web Text)

Max Activating Token Index: 297

Text #10

Max Range: 2.4241. Min Range: -2.4241

Max Act: 2.2873. Min Act: -0.1699

Data Index: 1404302 (Open Web Text)

Max Activating Token Index: 100

Text #11

Max Range: 2.4241. Min Range: -2.4241

Max Act: 2.2751. Min Act: -0.1699

Data Index: 8807046 (Open Web Text)

Max Activating Token Index: 738

Text #12

Max Range: 2.4241. Min Range: -2.4241

Max Act: 2.2572. Min Act: -0.1700

Data Index: 4847082 (Open Web Text)

Max Activating Token Index: 640

Text #13

Max Range: 2.4241. Min Range: -2.4241

Max Act: 2.2654. Min Act: -0.1700

Data Index: 457324 (Open Web Text)

Max Activating Token Index: 224

Text #14

Max Range: 2.4241. Min Range: -2.4241

Max Act: 2.2748. Min Act: -0.1699

Data Index: 6814857 (Open Web Text)

Max Activating Token Index: 521

Text #15

Max Range: 2.4241. Min Range: -2.4241

Max Act: 2.2845. Min Act: -0.1699

Data Index: 3229403 (Open Web Text)

Max Activating Token Index: 402

Text #16

Max Range: 2.4241. Min Range: -2.4241

Max Act: 2.2743. Min Act: -0.1699

Data Index: 4317494 (Open Web Text)

Max Activating Token Index: 36

Text #17

Max Range: 2.4241. Min Range: -2.4241

Max Act: 2.2747. Min Act: -0.1698

Data Index: 1132112 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 2.4241. Min Range: -2.4241

Max Act: 2.2747. Min Act: -0.1700

Data Index: 5518453 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 2.4241. Min Range: -2.4241

Max Act: 2.2684. Min Act: -0.1697

Data Index: 3718876 (Open Web Text)

Max Activating Token Index: 642