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

Dataset: Open Web Text

Neuron 1871 in Layer 0

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: 6.2505. Min Range: -6.2505

Max Act: 6.2505. Min Act: -0.1700

Data Index: 5829889 (Open Web Text)

Max Activating Token Index: 640

Text #1

Max Range: 6.2505. Min Range: -6.2505

Max Act: 5.8440. Min Act: -0.1700

Data Index: 4270816 (Open Web Text)

Max Activating Token Index: 611

Text #2

Max Range: 6.2505. Min Range: -6.2505

Max Act: 5.5896. Min Act: -0.1700

Data Index: 4028985 (Open Web Text)

Max Activating Token Index: 687

Text #3

Max Range: 6.2505. Min Range: -6.2505

Max Act: 5.6830. Min Act: -0.1700

Data Index: 6528477 (Open Web Text)

Max Activating Token Index: 586

Text #4

Max Range: 6.2505. Min Range: -6.2505

Max Act: 5.4878. Min Act: -0.1700

Data Index: 2335819 (Open Web Text)

Max Activating Token Index: 127

Text #5

Max Range: 6.2505. Min Range: -6.2505

Max Act: 5.3892. Min Act: -0.1700

Data Index: 7534367 (Open Web Text)

Max Activating Token Index: 619

Text #6

Max Range: 6.2505. Min Range: -6.2505

Max Act: 5.4925. Min Act: -0.1700

Data Index: 8454450 (Open Web Text)

Max Activating Token Index: 631

Text #7

Max Range: 6.2505. Min Range: -6.2505

Max Act: 5.4094. Min Act: -0.1700

Data Index: 857892 (Open Web Text)

Max Activating Token Index: 649

Text #8

Max Range: 6.2505. Min Range: -6.2505

Max Act: 5.4905. Min Act: -0.1700

Data Index: 2243875 (Open Web Text)

Max Activating Token Index: 641

Text #9

Max Range: 6.2505. Min Range: -6.2505

Max Act: 5.5290. Min Act: -0.1700

Data Index: 5393248 (Open Web Text)

Max Activating Token Index: 633

Text #10

Max Range: 6.2505. Min Range: -6.2505

Max Act: 5.4863. Min Act: -0.1700

Data Index: 230674 (Open Web Text)

Max Activating Token Index: 668

Text #11

Max Range: 6.2505. Min Range: -6.2505

Max Act: 5.4125. Min Act: -0.1700

Data Index: 7103864 (Open Web Text)

Max Activating Token Index: 589

Text #12

Max Range: 6.2505. Min Range: -6.2505

Max Act: 5.3796. Min Act: -0.1700

Data Index: 5370992 (Open Web Text)

Max Activating Token Index: 129

Text #13

Max Range: 6.2505. Min Range: -6.2505

Max Act: 5.3503. Min Act: -0.1700

Data Index: 4850562 (Open Web Text)

Max Activating Token Index: 598

Text #14

Max Range: 6.2505. Min Range: -6.2505

Max Act: 5.3405. Min Act: -0.1700

Data Index: 6068105 (Open Web Text)

Max Activating Token Index: 598

Text #15

Max Range: 6.2505. Min Range: -6.2505

Max Act: 5.2171. Min Act: -0.1700

Data Index: 2450582 (Open Web Text)

Max Activating Token Index: 623

Text #16

Max Range: 6.2505. Min Range: -6.2505

Max Act: 5.3254. Min Act: -0.1700

Data Index: 8085584 (Open Web Text)

Max Activating Token Index: 616

Text #17

Max Range: 6.2505. Min Range: -6.2505

Max Act: 5.2784. Min Act: -0.1700

Data Index: 5876919 (Open Web Text)

Max Activating Token Index: 648

Text #18

Max Range: 6.2505. Min Range: -6.2505

Max Act: 5.2749. Min Act: -0.1700

Data Index: 5485905 (Open Web Text)

Max Activating Token Index: 590

Text #19

Max Range: 6.2505. Min Range: -6.2505

Max Act: 5.2516. Min Act: -0.1700

Data Index: 6199799 (Open Web Text)

Max Activating Token Index: 654