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

Dataset: Open Web Text

Neuron 2987 in Layer 0

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: 1.4370. Min Range: -1.4370

Max Act: 1.4313. Min Act: -0.1655

Data Index: 806750 (Open Web Text)

Max Activating Token Index: 870

Text #1

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.4370. Min Act: -0.1655

Data Index: 5250654 (Open Web Text)

Max Activating Token Index: 132

Text #2

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.4180. Min Act: -0.1655

Data Index: 2867951 (Open Web Text)

Max Activating Token Index: 467

Text #3

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.4133. Min Act: -0.1655

Data Index: 5858831 (Open Web Text)

Max Activating Token Index: 135

Text #4

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.4011. Min Act: -0.1655

Data Index: 6137382 (Open Web Text)

Max Activating Token Index: 154

Text #5

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.3995. Min Act: -0.1655

Data Index: 4386082 (Open Web Text)

Max Activating Token Index: 951

Text #6

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.4059. Min Act: -0.1655

Data Index: 3300484 (Open Web Text)

Max Activating Token Index: 56

Text #7

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.3968. Min Act: -0.1655

Data Index: 1188928 (Open Web Text)

Max Activating Token Index: 692

Text #8

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.3947. Min Act: -0.1655

Data Index: 773662 (Open Web Text)

Max Activating Token Index: 356

Text #9

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.3932. Min Act: -0.1655

Data Index: 548427 (Open Web Text)

Max Activating Token Index: 318

Text #10

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.3962. Min Act: -0.1655

Data Index: 2868383 (Open Web Text)

Max Activating Token Index: 869

Text #11

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.3789. Min Act: -0.1655

Data Index: 5051524 (Open Web Text)

Max Activating Token Index: 382

Text #12

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.3871. Min Act: -0.1655

Data Index: 3653345 (Open Web Text)

Max Activating Token Index: 456

Text #13

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.3881. Min Act: -0.1655

Data Index: 8831921 (Open Web Text)

Max Activating Token Index: 732

Text #14

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.3833. Min Act: -0.1655

Data Index: 4555683 (Open Web Text)

Max Activating Token Index: 699

Text #15

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.3787. Min Act: -0.1655

Data Index: 8340386 (Open Web Text)

Max Activating Token Index: 443

Text #16

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.3730. Min Act: -0.1655

Data Index: 8204915 (Open Web Text)

Max Activating Token Index: 691

Text #17

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.3732. Min Act: -0.1655

Data Index: 1950711 (Open Web Text)

Max Activating Token Index: 386

Text #18

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.3753. Min Act: -0.1655

Data Index: 2692422 (Open Web Text)

Max Activating Token Index: 848

Text #19

Max Range: 1.4370. Min Range: -1.4370

Max Act: 1.3687. Min Act: -0.1655

Data Index: 3876063 (Open Web Text)

Max Activating Token Index: 833