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

Dataset: Open Web Text

Neuron 364 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: 2.0721. Min Range: -2.0721

Max Act: 2.0721. Min Act: -0.1700

Data Index: 7850438 (Open Web Text)

Max Activating Token Index: 357

Text #1

Max Range: 2.0721. Min Range: -2.0721

Max Act: 2.0613. Min Act: -0.1700

Data Index: 5043230 (Open Web Text)

Max Activating Token Index: 40

Text #2

Max Range: 2.0721. Min Range: -2.0721

Max Act: 2.0295. Min Act: -0.1700

Data Index: 4485776 (Open Web Text)

Max Activating Token Index: 292

Text #3

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.9983. Min Act: -0.1700

Data Index: 6184301 (Open Web Text)

Max Activating Token Index: 592

Text #4

Max Range: 2.0721. Min Range: -2.0721

Max Act: 2.0069. Min Act: -0.1700

Data Index: 6866528 (Open Web Text)

Max Activating Token Index: 576

Text #5

Max Range: 2.0721. Min Range: -2.0721

Max Act: 2.0123. Min Act: -0.1700

Data Index: 3730124 (Open Web Text)

Max Activating Token Index: 536

Text #6

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.9853. Min Act: -0.1700

Data Index: 686291 (Open Web Text)

Max Activating Token Index: 924

Text #7

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.9868. Min Act: -0.1700

Data Index: 6497083 (Open Web Text)

Max Activating Token Index: 456

Text #8

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.9952. Min Act: -0.1700

Data Index: 1349335 (Open Web Text)

Max Activating Token Index: 98

Text #9

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.9910. Min Act: -0.1700

Data Index: 7368286 (Open Web Text)

Max Activating Token Index: 152

Text #10

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.9749. Min Act: -0.1700

Data Index: 8543907 (Open Web Text)

Max Activating Token Index: 442

Text #11

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.9721. Min Act: -0.1700

Data Index: 1713173 (Open Web Text)

Max Activating Token Index: 661

Text #12

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.9670. Min Act: -0.1700

Data Index: 7489381 (Open Web Text)

Max Activating Token Index: 890

Text #13

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.9799. Min Act: -0.1700

Data Index: 3416427 (Open Web Text)

Max Activating Token Index: 474

Text #14

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.9774. Min Act: -0.1700

Data Index: 3389404 (Open Web Text)

Max Activating Token Index: 134

Text #15

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.9887. Min Act: -0.1700

Data Index: 285299 (Open Web Text)

Max Activating Token Index: 689

Text #16

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.9769. Min Act: -0.1700

Data Index: 1606039 (Open Web Text)

Max Activating Token Index: 295

Text #17

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.9778. Min Act: -0.1700

Data Index: 2458511 (Open Web Text)

Max Activating Token Index: 514

Text #18

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.9781. Min Act: -0.1700

Data Index: 6866924 (Open Web Text)

Max Activating Token Index: 151

Text #19

Max Range: 2.0721. Min Range: -2.0721

Max Act: 1.9655. Min Act: -0.1700

Data Index: 2140902 (Open Web Text)

Max Activating Token Index: 149