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

Dataset: Open Web Text

Neuron 345 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: 4.7908. Min Range: -4.7908

Max Act: 4.7908. Min Act: -0.1700

Data Index: 6238490 (Open Web Text)

Max Activating Token Index: 43

Text #1

Max Range: 4.7908. Min Range: -4.7908

Max Act: 4.6460. Min Act: -0.1700

Data Index: 7607258 (Open Web Text)

Max Activating Token Index: 669

Text #2

Max Range: 4.7908. Min Range: -4.7908

Max Act: 4.6497. Min Act: -0.1700

Data Index: 2387949 (Open Web Text)

Max Activating Token Index: 625

Text #3

Max Range: 4.7908. Min Range: -4.7908

Max Act: 4.5922. Min Act: -0.1700

Data Index: 4426984 (Open Web Text)

Max Activating Token Index: 318

Text #4

Max Range: 4.7908. Min Range: -4.7908

Max Act: 4.6357. Min Act: -0.1700

Data Index: 8550322 (Open Web Text)

Max Activating Token Index: 716

Text #5

Max Range: 4.7908. Min Range: -4.7908

Max Act: 4.5671. Min Act: -0.1700

Data Index: 3022918 (Open Web Text)

Max Activating Token Index: 502

Text #6

Max Range: 4.7908. Min Range: -4.7908

Max Act: 4.5959. Min Act: -0.1700

Data Index: 8274304 (Open Web Text)

Max Activating Token Index: 817

Text #7

Max Range: 4.7908. Min Range: -4.7908

Max Act: 4.5858. Min Act: -0.1700

Data Index: 8789514 (Open Web Text)

Max Activating Token Index: 982

Text #8

Max Range: 4.7908. Min Range: -4.7908

Max Act: 4.5853. Min Act: -0.1700

Data Index: 8333800 (Open Web Text)

Max Activating Token Index: 784

Text #9

Max Range: 4.7908. Min Range: -4.7908

Max Act: 4.5266. Min Act: -0.1700

Data Index: 2719103 (Open Web Text)

Max Activating Token Index: 422

Text #10

Max Range: 4.7908. Min Range: -4.7908

Max Act: 4.5181. Min Act: -0.1700

Data Index: 9045 (Open Web Text)

Max Activating Token Index: 736

Text #11

Max Range: 4.7908. Min Range: -4.7908

Max Act: 4.5125. Min Act: -0.1700

Data Index: 7805217 (Open Web Text)

Max Activating Token Index: 365

Text #12

Max Range: 4.7908. Min Range: -4.7908

Max Act: 4.4803. Min Act: -0.1700

Data Index: 457590 (Open Web Text)

Max Activating Token Index: 179

Text #13

Max Range: 4.7908. Min Range: -4.7908

Max Act: 4.4726. Min Act: -0.1700

Data Index: 5556363 (Open Web Text)

Max Activating Token Index: 482

Text #14

Max Range: 4.7908. Min Range: -4.7908

Max Act: 4.4700. Min Act: -0.1700

Data Index: 1467807 (Open Web Text)

Max Activating Token Index: 537

Text #15

Max Range: 4.7908. Min Range: -4.7908

Max Act: 4.4630. Min Act: -0.1700

Data Index: 8476758 (Open Web Text)

Max Activating Token Index: 121

Text #16

Max Range: 4.7908. Min Range: -4.7908

Max Act: 4.5036. Min Act: -0.1700

Data Index: 1937832 (Open Web Text)

Max Activating Token Index: 972

Text #17

Max Range: 4.7908. Min Range: -4.7908

Max Act: 4.4974. Min Act: -0.1700

Data Index: 2195498 (Open Web Text)

Max Activating Token Index: 46

Text #18

Max Range: 4.7908. Min Range: -4.7908

Max Act: 4.4724. Min Act: -0.1700

Data Index: 3690574 (Open Web Text)

Max Activating Token Index: 875

Text #19

Max Range: 4.7908. Min Range: -4.7908

Max Act: 4.4600. Min Act: -0.1700

Data Index: 198661 (Open Web Text)

Max Activating Token Index: 398