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

Dataset: Open Web Text

Neuron 2844 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: 0.8885. Min Range: -0.8885

Max Act: 0.8885. Min Act: -0.1306

Data Index: 1266191 (Open Web Text)

Max Activating Token Index: 352

Text #1

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.8720. Min Act: -0.1270

Data Index: 1273520 (Open Web Text)

Max Activating Token Index: 14

Text #2

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.8740. Min Act: -0.1253

Data Index: 5326087 (Open Web Text)

Max Activating Token Index: 956

Text #3

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.8766. Min Act: -0.1217

Data Index: 5821875 (Open Web Text)

Max Activating Token Index: 953

Text #4

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.8682. Min Act: -0.1133

Data Index: 4835385 (Open Web Text)

Max Activating Token Index: 610

Text #5

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.8642. Min Act: -0.1021

Data Index: 6526263 (Open Web Text)

Max Activating Token Index: 346

Text #6

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.8668. Min Act: -0.0862

Data Index: 1047546 (Open Web Text)

Max Activating Token Index: 13

Text #7

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.8598. Min Act: -0.1067

Data Index: 4277925 (Open Web Text)

Max Activating Token Index: 884

Text #8

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.8515. Min Act: -0.1078

Data Index: 7244515 (Open Web Text)

Max Activating Token Index: 974

Text #9

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.8636. Min Act: -0.1040

Data Index: 6281329 (Open Web Text)

Max Activating Token Index: 662

Text #10

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.8591. Min Act: -0.0927

Data Index: 931668 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.8543. Min Act: -0.1133

Data Index: 2014787 (Open Web Text)

Max Activating Token Index: 940

Text #12

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.8592. Min Act: -0.0403

Data Index: 4574129 (Open Web Text)

Max Activating Token Index: 901

Text #13

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.8613. Min Act: -0.1018

Data Index: 5681153 (Open Web Text)

Max Activating Token Index: 1018

Text #14

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.8617. Min Act: -0.1367

Data Index: 8050678 (Open Web Text)

Max Activating Token Index: 16

Text #15

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.8615. Min Act: -0.0887

Data Index: 1430023 (Open Web Text)

Max Activating Token Index: 680

Text #16

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.8501. Min Act: -0.1016

Data Index: 5801731 (Open Web Text)

Max Activating Token Index: 659

Text #17

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.8493. Min Act: -0.1049

Data Index: 6120836 (Open Web Text)

Max Activating Token Index: 938

Text #18

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.8452. Min Act: -0.1050

Data Index: 2496400 (Open Web Text)

Max Activating Token Index: 911

Text #19

Max Range: 0.8885. Min Range: -0.8885

Max Act: 0.8495. Min Act: -0.1133

Data Index: 3792067 (Open Web Text)

Max Activating Token Index: 605