Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2974 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4984. Min Range: -6.4984
Max Act: 6.4984. Min Act: -0.1700
Data Index: 365006 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4984. Min Range: -6.4984
Max Act: 5.9047. Min Act: -0.1700
Data Index: 4997527 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4984. Min Range: -6.4984
Max Act: 5.8422. Min Act: -0.1700
Data Index: 1283126 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4984. Min Range: -6.4984
Max Act: 5.8422. Min Act: -0.1700
Data Index: 2874331 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4984. Min Range: -6.4984
Max Act: 5.8109. Min Act: -0.1700
Data Index: 6342358 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4984. Min Range: -6.4984
Max Act: 5.7484. Min Act: -0.1700
Data Index: 6915075 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4984. Min Range: -6.4984
Max Act: 5.7172. Min Act: -0.1700
Data Index: 5406555 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4984. Min Range: -6.4984
Max Act: 5.7484. Min Act: -0.1700
Data Index: 2920742 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4984. Min Range: -6.4984
Max Act: 5.7484. Min Act: -0.1700
Data Index: 6753353 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4984. Min Range: -6.4984
Max Act: 5.7172. Min Act: -0.1700
Data Index: 4391457 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4984. Min Range: -6.4984
Max Act: 5.6859. Min Act: -0.1700
Data Index: 4084446 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4984. Min Range: -6.4984
Max Act: 5.6547. Min Act: -0.1700
Data Index: 7252814 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4984. Min Range: -6.4984
Max Act: 5.6547. Min Act: -0.1700
Data Index: 1912726 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4984. Min Range: -6.4984
Max Act: 5.6547. Min Act: -0.1700
Data Index: 4414409 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4984. Min Range: -6.4984
Max Act: 5.6547. Min Act: -0.1700
Data Index: 4457620 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4984. Min Range: -6.4984
Max Act: 5.6234. Min Act: -0.1700
Data Index: 6783250 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4984. Min Range: -6.4984
Max Act: 5.6234. Min Act: -0.1700
Data Index: 737221 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4984. Min Range: -6.4984
Max Act: 5.6234. Min Act: -0.1700
Data Index: 6994958 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4984. Min Range: -6.4984
Max Act: 5.6234. Min Act: -0.1700
Data Index: 3251855 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4984. Min Range: -6.4984
Max Act: 5.5922. Min Act: -0.1700
Data Index: 3622875 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19