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

Dataset: Open Web Text

Neuron 1934 in Layer 5

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: 6.0768. Min Range: -6.0768

Max Act: 6.0768. Min Act: -0.1700

Data Index: 6599802 (Open Web Text)

Max Activating Token Index: 958

Text #1

Max Range: 6.0768. Min Range: -6.0768

Max Act: 6.0300. Min Act: -0.1700

Data Index: 33149 (Open Web Text)

Max Activating Token Index: 544

Text #2

Max Range: 6.0768. Min Range: -6.0768

Max Act: 5.9272. Min Act: -0.1700

Data Index: 7242350 (Open Web Text)

Max Activating Token Index: 760

Text #3

Max Range: 6.0768. Min Range: -6.0768

Max Act: 5.9749. Min Act: -0.1700

Data Index: 3298458 (Open Web Text)

Max Activating Token Index: 359

Text #4

Max Range: 6.0768. Min Range: -6.0768

Max Act: 5.9659. Min Act: -0.1700

Data Index: 5229644 (Open Web Text)

Max Activating Token Index: 506

Text #5

Max Range: 6.0768. Min Range: -6.0768

Max Act: 5.9012. Min Act: -0.1700

Data Index: 2588729 (Open Web Text)

Max Activating Token Index: 161

Text #6

Max Range: 6.0768. Min Range: -6.0768

Max Act: 5.9130. Min Act: -0.1700

Data Index: 4459682 (Open Web Text)

Max Activating Token Index: 497

Text #7

Max Range: 6.0768. Min Range: -6.0768

Max Act: 5.8724. Min Act: -0.1700

Data Index: 3500090 (Open Web Text)

Max Activating Token Index: 455

Text #8

Max Range: 6.0768. Min Range: -6.0768

Max Act: 5.8866. Min Act: -0.1700

Data Index: 2335340 (Open Web Text)

Max Activating Token Index: 840

Text #9

Max Range: 6.0768. Min Range: -6.0768

Max Act: 5.8680. Min Act: -0.1700

Data Index: 2786671 (Open Web Text)

Max Activating Token Index: 485

Text #10

Max Range: 6.0768. Min Range: -6.0768

Max Act: 5.7928. Min Act: -0.1700

Data Index: 3842363 (Open Web Text)

Max Activating Token Index: 476

Text #11

Max Range: 6.0768. Min Range: -6.0768

Max Act: 5.8322. Min Act: -0.1700

Data Index: 5222639 (Open Web Text)

Max Activating Token Index: 896

Text #12

Max Range: 6.0768. Min Range: -6.0768

Max Act: 5.7878. Min Act: -0.1700

Data Index: 3368719 (Open Web Text)

Max Activating Token Index: 671

Text #13

Max Range: 6.0768. Min Range: -6.0768

Max Act: 5.7842. Min Act: -0.1700

Data Index: 6354959 (Open Web Text)

Max Activating Token Index: 915

Text #14

Max Range: 6.0768. Min Range: -6.0768

Max Act: 5.8600. Min Act: -0.1700

Data Index: 4402411 (Open Web Text)

Max Activating Token Index: 872

Text #15

Max Range: 6.0768. Min Range: -6.0768

Max Act: 5.7471. Min Act: -0.1700

Data Index: 2576626 (Open Web Text)

Max Activating Token Index: 757

Text #16

Max Range: 6.0768. Min Range: -6.0768

Max Act: 5.7705. Min Act: -0.1700

Data Index: 980161 (Open Web Text)

Max Activating Token Index: 783

Text #17

Max Range: 6.0768. Min Range: -6.0768

Max Act: 5.7362. Min Act: -0.1700

Data Index: 7239838 (Open Web Text)

Max Activating Token Index: 467

Text #18

Max Range: 6.0768. Min Range: -6.0768

Max Act: 5.7307. Min Act: -0.1700

Data Index: 8507040 (Open Web Text)

Max Activating Token Index: 915

Text #19

Max Range: 6.0768. Min Range: -6.0768

Max Act: 5.6967. Min Act: -0.1700

Data Index: 5876324 (Open Web Text)

Max Activating Token Index: 721