Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3293 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5071. Min Range: -7.5071
Max Act: 7.5071. Min Act: -0.1700
Data Index: 424848 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5071. Min Range: -7.5071
Max Act: 7.2258. Min Act: -0.1700
Data Index: 3899593 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5071. Min Range: -7.5071
Max Act: 7.1633. Min Act: -0.1700
Data Index: 475623 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5071. Min Range: -7.5071
Max Act: 7.0071. Min Act: -0.1700
Data Index: 5042240 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5071. Min Range: -7.5071
Max Act: 6.9758. Min Act: -0.1700
Data Index: 511423 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5071. Min Range: -7.5071
Max Act: 6.9758. Min Act: -0.1700
Data Index: 5104425 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5071. Min Range: -7.5071
Max Act: 6.9758. Min Act: -0.1700
Data Index: 1887048 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5071. Min Range: -7.5071
Max Act: 6.9758. Min Act: -0.1700
Data Index: 4631584 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5071. Min Range: -7.5071
Max Act: 6.9133. Min Act: -0.1700
Data Index: 1838817 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5071. Min Range: -7.5071
Max Act: 6.8821. Min Act: -0.1700
Data Index: 803220 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5071. Min Range: -7.5071
Max Act: 6.8508. Min Act: -0.1700
Data Index: 1734706 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5071. Min Range: -7.5071
Max Act: 6.7883. Min Act: -0.1700
Data Index: 7416254 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5071. Min Range: -7.5071
Max Act: 6.7883. Min Act: -0.1700
Data Index: 2879984 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5071. Min Range: -7.5071
Max Act: 6.7883. Min Act: -0.1700
Data Index: 6207008 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5071. Min Range: -7.5071
Max Act: 6.7571. Min Act: -0.1700
Data Index: 2026043 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5071. Min Range: -7.5071
Max Act: 6.7571. Min Act: -0.1700
Data Index: 1621435 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5071. Min Range: -7.5071
Max Act: 6.7571. Min Act: -0.1700
Data Index: 443907 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5071. Min Range: -7.5071
Max Act: 6.7258. Min Act: -0.1700
Data Index: 1710850 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5071. Min Range: -7.5071
Max Act: 6.7571. Min Act: -0.1700
Data Index: 8622291 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5071. Min Range: -7.5071
Max Act: 6.6321. Min Act: -0.1700
Data Index: 734528 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19