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

Dataset: Open Web Text

Neuron 4 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: 1.8297. Min Range: -1.8297

Max Act: 1.8206. Min Act: -0.1700

Data Index: 3207897 (Open Web Text)

Max Activating Token Index: 146

Text #1

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.8297. Min Act: -0.1700

Data Index: 7819746 (Open Web Text)

Max Activating Token Index: 784

Text #2

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.8129. Min Act: -0.1700

Data Index: 8337816 (Open Web Text)

Max Activating Token Index: 198

Text #3

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.8100. Min Act: -0.1700

Data Index: 6132666 (Open Web Text)

Max Activating Token Index: 883

Text #4

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.8131. Min Act: -0.1700

Data Index: 6331442 (Open Web Text)

Max Activating Token Index: 698

Text #5

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.7999. Min Act: -0.1700

Data Index: 312318 (Open Web Text)

Max Activating Token Index: 693

Text #6

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.7971. Min Act: -0.1700

Data Index: 7434343 (Open Web Text)

Max Activating Token Index: 637

Text #7

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.7940. Min Act: -0.1700

Data Index: 648099 (Open Web Text)

Max Activating Token Index: 196

Text #8

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.7717. Min Act: -0.1700

Data Index: 2311090 (Open Web Text)

Max Activating Token Index: 185

Text #9

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.7772. Min Act: -0.1700

Data Index: 8590398 (Open Web Text)

Max Activating Token Index: 60

Text #10

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.7757. Min Act: -0.1700

Data Index: 4890188 (Open Web Text)

Max Activating Token Index: 392

Text #11

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.7784. Min Act: -0.1700

Data Index: 8220351 (Open Web Text)

Max Activating Token Index: 182

Text #12

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.7731. Min Act: -0.1700

Data Index: 6730832 (Open Web Text)

Max Activating Token Index: 138

Text #13

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.7706. Min Act: -0.1700

Data Index: 16848 (Open Web Text)

Max Activating Token Index: 1001

Text #14

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.7754. Min Act: -0.1700

Data Index: 7005276 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.7759. Min Act: -0.1700

Data Index: 6709645 (Open Web Text)

Max Activating Token Index: 45

Text #16

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.7661. Min Act: -0.1700

Data Index: 5078628 (Open Web Text)

Max Activating Token Index: 267

Text #17

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.7615. Min Act: -0.1700

Data Index: 2732765 (Open Web Text)

Max Activating Token Index: 229

Text #18

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.7668. Min Act: -0.1700

Data Index: 957174 (Open Web Text)

Max Activating Token Index: 336

Text #19

Max Range: 1.8297. Min Range: -1.8297

Max Act: 1.7665. Min Act: -0.1700

Data Index: 5765141 (Open Web Text)

Max Activating Token Index: 83