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

Dataset: Open Web Text

Neuron 1365 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: 1.4927. Min Range: -1.4927

Max Act: 1.4902. Min Act: -0.1700

Data Index: 7508563 (Open Web Text)

Max Activating Token Index: 379

Text #1

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4927. Min Act: -0.1700

Data Index: 2693167 (Open Web Text)

Max Activating Token Index: 292

Text #2

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4590. Min Act: -0.1700

Data Index: 5170844 (Open Web Text)

Max Activating Token Index: 529

Text #3

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4578. Min Act: -0.1700

Data Index: 1829874 (Open Web Text)

Max Activating Token Index: 231

Text #4

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4403. Min Act: -0.1700

Data Index: 8739436 (Open Web Text)

Max Activating Token Index: 420

Text #5

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4207. Min Act: -0.1700

Data Index: 6638607 (Open Web Text)

Max Activating Token Index: 948

Text #6

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4354. Min Act: -0.1700

Data Index: 7967787 (Open Web Text)

Max Activating Token Index: 544

Text #7

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4319. Min Act: -0.1700

Data Index: 171785 (Open Web Text)

Max Activating Token Index: 560

Text #8

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4343. Min Act: -0.1700

Data Index: 3969192 (Open Web Text)

Max Activating Token Index: 499

Text #9

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4175. Min Act: -0.1700

Data Index: 7573573 (Open Web Text)

Max Activating Token Index: 523

Text #10

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4063. Min Act: -0.1700

Data Index: 8825601 (Open Web Text)

Max Activating Token Index: 261

Text #11

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.3953. Min Act: -0.1700

Data Index: 4825473 (Open Web Text)

Max Activating Token Index: 374

Text #12

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4003. Min Act: -0.1700

Data Index: 4687315 (Open Web Text)

Max Activating Token Index: 808

Text #13

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.3926. Min Act: -0.1700

Data Index: 5340676 (Open Web Text)

Max Activating Token Index: 672

Text #14

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.3943. Min Act: -0.1700

Data Index: 6580044 (Open Web Text)

Max Activating Token Index: 383

Text #15

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.3947. Min Act: -0.1700

Data Index: 6404254 (Open Web Text)

Max Activating Token Index: 819

Text #16

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.3969. Min Act: -0.1700

Data Index: 3864893 (Open Web Text)

Max Activating Token Index: 324

Text #17

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.3911. Min Act: -0.1700

Data Index: 8435833 (Open Web Text)

Max Activating Token Index: 714

Text #18

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.3847. Min Act: -0.1700

Data Index: 4268983 (Open Web Text)

Max Activating Token Index: 682

Text #19

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.3817. Min Act: -0.1700

Data Index: 3739933 (Open Web Text)

Max Activating Token Index: 924