Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3454 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1489. Min Range: -5.1489
Max Act: 5.1489. Min Act: -0.1700
Data Index: 3449270 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1489. Min Range: -5.1489
Max Act: 5.0551. Min Act: -0.1700
Data Index: 1328853 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.9926. Min Act: -0.1700
Data Index: 1038506 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.9301. Min Act: -0.1700
Data Index: 4566492 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.9301. Min Act: -0.1700
Data Index: 5913137 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8676. Min Act: -0.1700
Data Index: 8657466 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8676. Min Act: -0.1700
Data Index: 5949408 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8364. Min Act: -0.1700
Data Index: 460955 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8051. Min Act: -0.1700
Data Index: 7066339 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8051. Min Act: -0.1700
Data Index: 7628864 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.7739. Min Act: -0.1700
Data Index: 1335802 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.8051. Min Act: -0.1700
Data Index: 6492237 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.7426. Min Act: -0.1700
Data Index: 8806962 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.7114. Min Act: -0.1700
Data Index: 2556138 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.6801. Min Act: -0.1700
Data Index: 1074491 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.7114. Min Act: -0.1700
Data Index: 2943806 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.6801. Min Act: -0.1700
Data Index: 8545513 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.6801. Min Act: -0.1700
Data Index: 2839598 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.6489. Min Act: -0.1700
Data Index: 3269838 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1489. Min Range: -5.1489
Max Act: 4.6489. Min Act: -0.1700
Data Index: 6889033 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #19