Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 696 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7766. Min Range: -5.7766
Max Act: 5.7766. Min Act: -0.1700
Data Index: 4214374 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7766. Min Range: -5.7766
Max Act: 5.7141. Min Act: -0.1700
Data Index: 277595 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7766. Min Range: -5.7766
Max Act: 5.5891. Min Act: -0.1700
Data Index: 8768730 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7766. Min Range: -5.7766
Max Act: 5.4016. Min Act: -0.1700
Data Index: 5187209 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7766. Min Range: -5.7766
Max Act: 5.3703. Min Act: -0.1700
Data Index: 1381854 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7766. Min Range: -5.7766
Max Act: 5.2453. Min Act: -0.1700
Data Index: 397022 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7766. Min Range: -5.7766
Max Act: 5.2766. Min Act: -0.1700
Data Index: 5083176 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7766. Min Range: -5.7766
Max Act: 5.2766. Min Act: -0.1700
Data Index: 7431937 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7766. Min Range: -5.7766
Max Act: 5.2766. Min Act: -0.1700
Data Index: 7009840 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7766. Min Range: -5.7766
Max Act: 5.2141. Min Act: -0.1700
Data Index: 2951429 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7766. Min Range: -5.7766
Max Act: 5.1828. Min Act: -0.1700
Data Index: 6956465 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7766. Min Range: -5.7766
Max Act: 5.1828. Min Act: -0.1700
Data Index: 7110502 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7766. Min Range: -5.7766
Max Act: 5.1828. Min Act: -0.1700
Data Index: 1521292 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7766. Min Range: -5.7766
Max Act: 5.1828. Min Act: -0.1700
Data Index: 967488 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7766. Min Range: -5.7766
Max Act: 5.1828. Min Act: -0.1700
Data Index: 8611823 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7766. Min Range: -5.7766
Max Act: 5.1203. Min Act: -0.1700
Data Index: 396480 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7766. Min Range: -5.7766
Max Act: 5.0891. Min Act: -0.1699
Data Index: 7750620 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7766. Min Range: -5.7766
Max Act: 5.1203. Min Act: -0.1700
Data Index: 646674 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7766. Min Range: -5.7766
Max Act: 5.1203. Min Act: -0.1700
Data Index: 8173781 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7766. Min Range: -5.7766
Max Act: 5.1203. Min Act: -0.1700
Data Index: 6313112 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19