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

Dataset: Open Web Text

Neuron 953 in Layer 3

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: 4.5886. Min Range: -4.5886

Max Act: 4.5886. Min Act: -0.1700

Data Index: 6178924 (Open Web Text)

Max Activating Token Index: 666

Text #1

Max Range: 4.5886. Min Range: -4.5886

Max Act: 4.4992. Min Act: -0.1700

Data Index: 1530144 (Open Web Text)

Max Activating Token Index: 226

Text #2

Max Range: 4.5886. Min Range: -4.5886

Max Act: 4.5458. Min Act: -0.1700

Data Index: 2950088 (Open Web Text)

Max Activating Token Index: 713

Text #3

Max Range: 4.5886. Min Range: -4.5886

Max Act: 4.5311. Min Act: -0.1700

Data Index: 8299815 (Open Web Text)

Max Activating Token Index: 806

Text #4

Max Range: 4.5886. Min Range: -4.5886

Max Act: 4.4926. Min Act: -0.1700

Data Index: 8782684 (Open Web Text)

Max Activating Token Index: 633

Text #5

Max Range: 4.5886. Min Range: -4.5886

Max Act: 4.5090. Min Act: -0.1700

Data Index: 4651466 (Open Web Text)

Max Activating Token Index: 149

Text #6

Max Range: 4.5886. Min Range: -4.5886

Max Act: 4.5090. Min Act: -0.1700

Data Index: 4488110 (Open Web Text)

Max Activating Token Index: 330

Text #7

Max Range: 4.5886. Min Range: -4.5886

Max Act: 4.4515. Min Act: -0.1700

Data Index: 2333155 (Open Web Text)

Max Activating Token Index: 116

Text #8

Max Range: 4.5886. Min Range: -4.5886

Max Act: 4.4571. Min Act: -0.1700

Data Index: 3076538 (Open Web Text)

Max Activating Token Index: 290

Text #9

Max Range: 4.5886. Min Range: -4.5886

Max Act: 4.4264. Min Act: -0.1700

Data Index: 7124027 (Open Web Text)

Max Activating Token Index: 605

Text #10

Max Range: 4.5886. Min Range: -4.5886

Max Act: 4.4194. Min Act: -0.1700

Data Index: 2475279 (Open Web Text)

Max Activating Token Index: 515

Text #11

Max Range: 4.5886. Min Range: -4.5886

Max Act: 4.3925. Min Act: -0.1700

Data Index: 3977279 (Open Web Text)

Max Activating Token Index: 178

Text #12

Max Range: 4.5886. Min Range: -4.5886

Max Act: 4.4123. Min Act: -0.1700

Data Index: 6911541 (Open Web Text)

Max Activating Token Index: 564

Text #13

Max Range: 4.5886. Min Range: -4.5886

Max Act: 4.3853. Min Act: -0.1700

Data Index: 616825 (Open Web Text)

Max Activating Token Index: 573

Text #14

Max Range: 4.5886. Min Range: -4.5886

Max Act: 4.4198. Min Act: -0.1700

Data Index: 1284969 (Open Web Text)

Max Activating Token Index: 302

Text #15

Max Range: 4.5886. Min Range: -4.5886

Max Act: 4.3776. Min Act: -0.1700

Data Index: 4366184 (Open Web Text)

Max Activating Token Index: 605

Text #16

Max Range: 4.5886. Min Range: -4.5886

Max Act: 4.3983. Min Act: -0.1700

Data Index: 3826843 (Open Web Text)

Max Activating Token Index: 570

Text #17

Max Range: 4.5886. Min Range: -4.5886

Max Act: 4.3819. Min Act: -0.1700

Data Index: 833443 (Open Web Text)

Max Activating Token Index: 106

Text #18

Max Range: 4.5886. Min Range: -4.5886

Max Act: 4.3817. Min Act: -0.1700

Data Index: 888281 (Open Web Text)

Max Activating Token Index: 380

Text #19

Max Range: 4.5886. Min Range: -4.5886

Max Act: 4.3929. Min Act: -0.1700

Data Index: 3164201 (Open Web Text)

Max Activating Token Index: 284