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

Dataset: Open Web Text

Neuron 1776 in Layer 6

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: 4.5217. Min Range: -4.5217

Max Act: 4.5217. Min Act: -0.1700

Data Index: 1509300 (Open Web Text)

Max Activating Token Index: 465

Text #1

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.4591. Min Act: -0.1700

Data Index: 3061258 (Open Web Text)

Max Activating Token Index: 703

Text #2

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.3909. Min Act: -0.1700

Data Index: 2784745 (Open Web Text)

Max Activating Token Index: 741

Text #3

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.3653. Min Act: -0.1700

Data Index: 8594443 (Open Web Text)

Max Activating Token Index: 591

Text #4

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.3452. Min Act: -0.1700

Data Index: 8482474 (Open Web Text)

Max Activating Token Index: 728

Text #5

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.3665. Min Act: -0.1700

Data Index: 5303317 (Open Web Text)

Max Activating Token Index: 619

Text #6

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.3604. Min Act: -0.1700

Data Index: 8427140 (Open Web Text)

Max Activating Token Index: 593

Text #7

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.3514. Min Act: -0.1700

Data Index: 2441822 (Open Web Text)

Max Activating Token Index: 971

Text #8

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.3204. Min Act: -0.1700

Data Index: 5061968 (Open Web Text)

Max Activating Token Index: 813

Text #9

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.3250. Min Act: -0.1700

Data Index: 5382462 (Open Web Text)

Max Activating Token Index: 297

Text #10

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.3456. Min Act: -0.1700

Data Index: 5887561 (Open Web Text)

Max Activating Token Index: 425

Text #11

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.2846. Min Act: -0.1700

Data Index: 920473 (Open Web Text)

Max Activating Token Index: 740

Text #12

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.2944. Min Act: -0.1700

Data Index: 7539965 (Open Web Text)

Max Activating Token Index: 740

Text #13

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.2872. Min Act: -0.1700

Data Index: 3299956 (Open Web Text)

Max Activating Token Index: 107

Text #14

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.2808. Min Act: -0.1700

Data Index: 3568114 (Open Web Text)

Max Activating Token Index: 549

Text #15

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.2633. Min Act: -0.1700

Data Index: 5161363 (Open Web Text)

Max Activating Token Index: 838

Text #16

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.2398. Min Act: -0.1700

Data Index: 8343654 (Open Web Text)

Max Activating Token Index: 788

Text #17

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.2455. Min Act: -0.1700

Data Index: 524158 (Open Web Text)

Max Activating Token Index: 974

Text #18

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.2198. Min Act: -0.1700

Data Index: 530677 (Open Web Text)

Max Activating Token Index: 592

Text #19

Max Range: 4.5217. Min Range: -4.5217

Max Act: 4.2369. Min Act: -0.1700

Data Index: 7239391 (Open Web Text)

Max Activating Token Index: 694