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

Dataset: Open Web Text

Neuron 2907 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: 4.6638. Min Range: -4.6638

Max Act: 4.6638. Min Act: -0.1700

Data Index: 7548595 (Open Web Text)

Max Activating Token Index: 613

Text #1

Max Range: 4.6638. Min Range: -4.6638

Max Act: 4.5623. Min Act: -0.1700

Data Index: 42407 (Open Web Text)

Max Activating Token Index: 266

Text #2

Max Range: 4.6638. Min Range: -4.6638

Max Act: 4.5028. Min Act: -0.1700

Data Index: 4367509 (Open Web Text)

Max Activating Token Index: 493

Text #3

Max Range: 4.6638. Min Range: -4.6638

Max Act: 4.4259. Min Act: -0.1700

Data Index: 4251213 (Open Web Text)

Max Activating Token Index: 334

Text #4

Max Range: 4.6638. Min Range: -4.6638

Max Act: 4.4716. Min Act: -0.1700

Data Index: 3480415 (Open Web Text)

Max Activating Token Index: 124

Text #5

Max Range: 4.6638. Min Range: -4.6638

Max Act: 4.4032. Min Act: -0.1700

Data Index: 3521072 (Open Web Text)

Max Activating Token Index: 293

Text #6

Max Range: 4.6638. Min Range: -4.6638

Max Act: 4.3345. Min Act: -0.1700

Data Index: 7559702 (Open Web Text)

Max Activating Token Index: 616

Text #7

Max Range: 4.6638. Min Range: -4.6638

Max Act: 4.4040. Min Act: -0.1700

Data Index: 310442 (Open Web Text)

Max Activating Token Index: 573

Text #8

Max Range: 4.6638. Min Range: -4.6638

Max Act: 4.3458. Min Act: -0.1700

Data Index: 1199583 (Open Web Text)

Max Activating Token Index: 602

Text #9

Max Range: 4.6638. Min Range: -4.6638

Max Act: 4.3770. Min Act: -0.1700

Data Index: 7384820 (Open Web Text)

Max Activating Token Index: 943

Text #10

Max Range: 4.6638. Min Range: -4.6638

Max Act: 4.2601. Min Act: -0.1700

Data Index: 3596780 (Open Web Text)

Max Activating Token Index: 853

Text #11

Max Range: 4.6638. Min Range: -4.6638

Max Act: 4.2882. Min Act: -0.1700

Data Index: 7878420 (Open Web Text)

Max Activating Token Index: 473

Text #12

Max Range: 4.6638. Min Range: -4.6638

Max Act: 4.3069. Min Act: -0.1700

Data Index: 395537 (Open Web Text)

Max Activating Token Index: 239

Text #13

Max Range: 4.6638. Min Range: -4.6638

Max Act: 4.3081. Min Act: -0.1700

Data Index: 745409 (Open Web Text)

Max Activating Token Index: 675

Text #14

Max Range: 4.6638. Min Range: -4.6638

Max Act: 4.2977. Min Act: -0.1700

Data Index: 1485842 (Open Web Text)

Max Activating Token Index: 250

Text #15

Max Range: 4.6638. Min Range: -4.6638

Max Act: 4.3423. Min Act: -0.1700

Data Index: 8338360 (Open Web Text)

Max Activating Token Index: 960

Text #16

Max Range: 4.6638. Min Range: -4.6638

Max Act: 4.2854. Min Act: -0.1700

Data Index: 2311688 (Open Web Text)

Max Activating Token Index: 927

Text #17

Max Range: 4.6638. Min Range: -4.6638

Max Act: 4.2496. Min Act: -0.1700

Data Index: 2126049 (Open Web Text)

Max Activating Token Index: 439

Text #18

Max Range: 4.6638. Min Range: -4.6638

Max Act: 4.2680. Min Act: -0.1700

Data Index: 3115363 (Open Web Text)

Max Activating Token Index: 841

Text #19

Max Range: 4.6638. Min Range: -4.6638

Max Act: 4.2187. Min Act: -0.1700

Data Index: 3407613 (Open Web Text)

Max Activating Token Index: 960