Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4525 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0621. Min Range: -7.0621
Max Act: 7.0621. Min Act: -0.1700
Data Index: 4463873 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0621. Min Range: -7.0621
Max Act: 7.0621. Min Act: -0.1700
Data Index: 3528728 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0621. Min Range: -7.0621
Max Act: 6.9996. Min Act: -0.1700
Data Index: 984202 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0621. Min Range: -7.0621
Max Act: 6.9683. Min Act: -0.1700
Data Index: 754064 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0621. Min Range: -7.0621
Max Act: 6.9683. Min Act: -0.1700
Data Index: 5928076 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0621. Min Range: -7.0621
Max Act: 6.8433. Min Act: -0.1700
Data Index: 2273501 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0621. Min Range: -7.0621
Max Act: 6.8746. Min Act: -0.1700
Data Index: 2523160 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0621. Min Range: -7.0621
Max Act: 6.8433. Min Act: -0.1700
Data Index: 4142090 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0621. Min Range: -7.0621
Max Act: 6.8433. Min Act: -0.1700
Data Index: 4601477 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0621. Min Range: -7.0621
Max Act: 6.8121. Min Act: -0.1700
Data Index: 2911198 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0621. Min Range: -7.0621
Max Act: 6.7808. Min Act: -0.1700
Data Index: 2428734 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0621. Min Range: -7.0621
Max Act: 6.7808. Min Act: -0.1700
Data Index: 7073289 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0621. Min Range: -7.0621
Max Act: 6.7183. Min Act: -0.1700
Data Index: 5244098 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0621. Min Range: -7.0621
Max Act: 6.7496. Min Act: -0.1700
Data Index: 2138271 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0621. Min Range: -7.0621
Max Act: 6.7496. Min Act: -0.1700
Data Index: 1017885 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0621. Min Range: -7.0621
Max Act: 6.7183. Min Act: -0.1700
Data Index: 6517387 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0621. Min Range: -7.0621
Max Act: 6.7183. Min Act: -0.1700
Data Index: 5142381 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0621. Min Range: -7.0621
Max Act: 6.6558. Min Act: -0.1700
Data Index: 7356750 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0621. Min Range: -7.0621
Max Act: 6.6558. Min Act: -0.1700
Data Index: 7533116 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0621. Min Range: -7.0621
Max Act: 6.6871. Min Act: -0.1700
Data Index: 1039410 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #19