Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2785 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6774. Min Range: -4.6774
Max Act: 4.6774. Min Act: -0.1700
Data Index: 6904609 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6774. Min Range: -4.6774
Max Act: 4.6462. Min Act: -0.1700
Data Index: 496208 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6774. Min Range: -4.6774
Max Act: 4.5837. Min Act: -0.1700
Data Index: 7954919 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6774. Min Range: -4.6774
Max Act: 4.6149. Min Act: -0.1700
Data Index: 3710053 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6774. Min Range: -4.6774
Max Act: 4.4899. Min Act: -0.1700
Data Index: 8229844 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6774. Min Range: -4.6774
Max Act: 4.4899. Min Act: -0.1700
Data Index: 5084068 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6774. Min Range: -4.6774
Max Act: 4.4899. Min Act: -0.1700
Data Index: 7906775 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6774. Min Range: -4.6774
Max Act: 4.4274. Min Act: -0.1700
Data Index: 7708024 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6774. Min Range: -4.6774
Max Act: 4.4274. Min Act: -0.1700
Data Index: 4329129 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6774. Min Range: -4.6774
Max Act: 4.4274. Min Act: -0.1700
Data Index: 4307769 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6774. Min Range: -4.6774
Max Act: 4.3962. Min Act: -0.1700
Data Index: 3430096 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6774. Min Range: -4.6774
Max Act: 4.3962. Min Act: -0.1700
Data Index: 7729318 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6774. Min Range: -4.6774
Max Act: 4.3962. Min Act: -0.1700
Data Index: 3392306 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6774. Min Range: -4.6774
Max Act: 4.3962. Min Act: -0.1700
Data Index: 5117225 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6774. Min Range: -4.6774
Max Act: 4.3962. Min Act: -0.1700
Data Index: 3910973 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6774. Min Range: -4.6774
Max Act: 4.3962. Min Act: -0.1700
Data Index: 2337044 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6774. Min Range: -4.6774
Max Act: 4.3962. Min Act: -0.1700
Data Index: 7706501 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6774. Min Range: -4.6774
Max Act: 4.3649. Min Act: -0.1700
Data Index: 5180809 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6774. Min Range: -4.6774
Max Act: 4.3336. Min Act: -0.1700
Data Index: 4580537 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6774. Min Range: -4.6774
Max Act: 4.3336. Min Act: -0.1700
Data Index: 6747257 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19