Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1075 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0126. Min Range: -6.0126
Max Act: 6.0126. Min Act: -0.1700
Data Index: 6374067 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0126. Min Range: -6.0126
Max Act: 5.9501. Min Act: -0.1700
Data Index: 2523450 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0126. Min Range: -6.0126
Max Act: 5.9501. Min Act: -0.1700
Data Index: 5670843 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0126. Min Range: -6.0126
Max Act: 5.8876. Min Act: -0.1700
Data Index: 8327138 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0126. Min Range: -6.0126
Max Act: 5.9189. Min Act: -0.1700
Data Index: 7125357 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0126. Min Range: -6.0126
Max Act: 5.8564. Min Act: -0.1700
Data Index: 7144802 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0126. Min Range: -6.0126
Max Act: 5.8564. Min Act: -0.1700
Data Index: 5254739 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0126. Min Range: -6.0126
Max Act: 5.7939. Min Act: -0.1700
Data Index: 6578708 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0126. Min Range: -6.0126
Max Act: 5.7939. Min Act: -0.1700
Data Index: 680317 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0126. Min Range: -6.0126
Max Act: 5.7939. Min Act: -0.1700
Data Index: 1427756 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0126. Min Range: -6.0126
Max Act: 5.7939. Min Act: -0.1700
Data Index: 8651192 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0126. Min Range: -6.0126
Max Act: 5.7314. Min Act: -0.1700
Data Index: 5087345 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0126. Min Range: -6.0126
Max Act: 5.7001. Min Act: -0.1700
Data Index: 3075820 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0126. Min Range: -6.0126
Max Act: 5.7001. Min Act: -0.1700
Data Index: 2400298 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0126. Min Range: -6.0126
Max Act: 5.7001. Min Act: -0.1700
Data Index: 5872226 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0126. Min Range: -6.0126
Max Act: 5.6689. Min Act: -0.1700
Data Index: 1557733 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0126. Min Range: -6.0126
Max Act: 5.6689. Min Act: -0.1700
Data Index: 3271996 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0126. Min Range: -6.0126
Max Act: 5.6376. Min Act: -0.1700
Data Index: 8261995 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0126. Min Range: -6.0126
Max Act: 5.6376. Min Act: -0.1700
Data Index: 3051848 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0126. Min Range: -6.0126
Max Act: 5.6376. Min Act: -0.1700
Data Index: 6410002 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19