Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4812 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5110. Min Range: -7.5110
Max Act: 7.5110. Min Act: -0.1700
Data Index: 6292312 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5110. Min Range: -7.5110
Max Act: 7.1360. Min Act: -0.1700
Data Index: 147005 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5110. Min Range: -7.5110
Max Act: 7.1360. Min Act: -0.1700
Data Index: 7722056 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5110. Min Range: -7.5110
Max Act: 7.1047. Min Act: -0.1700
Data Index: 796734 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5110. Min Range: -7.5110
Max Act: 7.0735. Min Act: -0.1700
Data Index: 5972941 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5110. Min Range: -7.5110
Max Act: 7.0110. Min Act: -0.1700
Data Index: 2920735 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5110. Min Range: -7.5110
Max Act: 6.9485. Min Act: -0.1700
Data Index: 2499403 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5110. Min Range: -7.5110
Max Act: 6.9485. Min Act: -0.1700
Data Index: 5565223 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5110. Min Range: -7.5110
Max Act: 6.6672. Min Act: -0.1700
Data Index: 2236509 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5110. Min Range: -7.5110
Max Act: 6.6047. Min Act: -0.1700
Data Index: 5193898 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5110. Min Range: -7.5110
Max Act: 6.5735. Min Act: -0.1700
Data Index: 276842 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5110. Min Range: -7.5110
Max Act: 6.6047. Min Act: -0.1700
Data Index: 446100 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5110. Min Range: -7.5110
Max Act: 6.5422. Min Act: -0.1700
Data Index: 5122270 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5110. Min Range: -7.5110
Max Act: 6.5422. Min Act: -0.1700
Data Index: 5112807 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5110. Min Range: -7.5110
Max Act: 6.5110. Min Act: -0.1700
Data Index: 4062709 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5110. Min Range: -7.5110
Max Act: 6.4797. Min Act: -0.1700
Data Index: 3260324 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5110. Min Range: -7.5110
Max Act: 6.4797. Min Act: -0.1700
Data Index: 4628861 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5110. Min Range: -7.5110
Max Act: 6.4485. Min Act: -0.1700
Data Index: 3023650 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5110. Min Range: -7.5110
Max Act: 6.4485. Min Act: -0.1700
Data Index: 5250252 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5110. Min Range: -7.5110
Max Act: 6.4172. Min Act: -0.1700
Data Index: 2009031 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19