Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5481 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4920. Min Range: -6.4920
Max Act: 6.4920. Min Act: -0.1700
Data Index: 3320449 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4920. Min Range: -6.4920
Max Act: 6.3983. Min Act: -0.1700
Data Index: 926128 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4920. Min Range: -6.4920
Max Act: 5.8983. Min Act: -0.1700
Data Index: 680631 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4920. Min Range: -6.4920
Max Act: 5.8983. Min Act: -0.1700
Data Index: 911452 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4920. Min Range: -6.4920
Max Act: 5.8670. Min Act: -0.1700
Data Index: 4108245 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4920. Min Range: -6.4920
Max Act: 5.8670. Min Act: -0.1700
Data Index: 2938887 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4920. Min Range: -6.4920
Max Act: 5.8358. Min Act: -0.1700
Data Index: 5190650 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4920. Min Range: -6.4920
Max Act: 5.8045. Min Act: -0.1700
Data Index: 5038469 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4920. Min Range: -6.4920
Max Act: 5.8045. Min Act: -0.1700
Data Index: 2990821 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4920. Min Range: -6.4920
Max Act: 5.7733. Min Act: -0.1700
Data Index: 1029099 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4920. Min Range: -6.4920
Max Act: 5.8045. Min Act: -0.1700
Data Index: 2846843 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4920. Min Range: -6.4920
Max Act: 5.7420. Min Act: -0.1700
Data Index: 3618691 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4920. Min Range: -6.4920
Max Act: 5.7733. Min Act: -0.1700
Data Index: 8630062 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4920. Min Range: -6.4920
Max Act: 5.7420. Min Act: -0.1700
Data Index: 5936394 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4920. Min Range: -6.4920
Max Act: 5.7420. Min Act: -0.1700
Data Index: 6159035 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4920. Min Range: -6.4920
Max Act: 5.7733. Min Act: -0.1700
Data Index: 4108244 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4920. Min Range: -6.4920
Max Act: 5.7108. Min Act: -0.1700
Data Index: 4401677 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4920. Min Range: -6.4920
Max Act: 5.7108. Min Act: -0.1700
Data Index: 4768831 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4920. Min Range: -6.4920
Max Act: 5.6795. Min Act: -0.1700
Data Index: 4508611 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4920. Min Range: -6.4920
Max Act: 5.7108. Min Act: -0.1700
Data Index: 6159034 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19