Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3787 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2430. Min Range: -5.2430
Max Act: 5.2430. Min Act: -0.1700
Data Index: 1683516 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2430. Min Range: -5.2430
Max Act: 5.0868. Min Act: -0.1700
Data Index: 8513418 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2430. Min Range: -5.2430
Max Act: 5.0243. Min Act: -0.1700
Data Index: 6683856 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2430. Min Range: -5.2430
Max Act: 4.9618. Min Act: -0.1700
Data Index: 8672061 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2430. Min Range: -5.2430
Max Act: 4.9305. Min Act: -0.1700
Data Index: 5877636 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2430. Min Range: -5.2430
Max Act: 4.8680. Min Act: -0.1700
Data Index: 706844 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2430. Min Range: -5.2430
Max Act: 4.8680. Min Act: -0.1700
Data Index: 643417 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2430. Min Range: -5.2430
Max Act: 4.8680. Min Act: -0.1700
Data Index: 1804355 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2430. Min Range: -5.2430
Max Act: 4.8680. Min Act: -0.1700
Data Index: 577144 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2430. Min Range: -5.2430
Max Act: 4.8368. Min Act: -0.1700
Data Index: 5566513 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2430. Min Range: -5.2430
Max Act: 4.8055. Min Act: -0.1700
Data Index: 3557388 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2430. Min Range: -5.2430
Max Act: 4.8055. Min Act: -0.1700
Data Index: 8732333 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2430. Min Range: -5.2430
Max Act: 4.7743. Min Act: -0.1700
Data Index: 764675 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2430. Min Range: -5.2430
Max Act: 4.7743. Min Act: -0.1700
Data Index: 805472 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2430. Min Range: -5.2430
Max Act: 4.7743. Min Act: -0.1700
Data Index: 1655143 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2430. Min Range: -5.2430
Max Act: 4.7743. Min Act: -0.1700
Data Index: 5462584 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2430. Min Range: -5.2430
Max Act: 4.7743. Min Act: -0.1700
Data Index: 1833482 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2430. Min Range: -5.2430
Max Act: 4.7743. Min Act: -0.1700
Data Index: 4126418 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2430. Min Range: -5.2430
Max Act: 4.7743. Min Act: -0.1700
Data Index: 1762434 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2430. Min Range: -5.2430
Max Act: 4.7430. Min Act: -0.1700
Data Index: 5739777 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19