Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5736 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2131. Min Range: -9.2131
Max Act: 9.2131. Min Act: -0.1700
Data Index: 5740542 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2131. Min Range: -9.2131
Max Act: 9.0881. Min Act: -0.1700
Data Index: 3553677 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2131. Min Range: -9.2131
Max Act: 9.0881. Min Act: -0.1700
Data Index: 4219042 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2131. Min Range: -9.2131
Max Act: 9.0881. Min Act: -0.1700
Data Index: 3696750 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2131. Min Range: -9.2131
Max Act: 9.0881. Min Act: -0.1700
Data Index: 5015338 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2131. Min Range: -9.2131
Max Act: 9.0256. Min Act: -0.1700
Data Index: 6097715 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2131. Min Range: -9.2131
Max Act: 9.0256. Min Act: -0.1700
Data Index: 1826647 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2131. Min Range: -9.2131
Max Act: 9.0256. Min Act: -0.1700
Data Index: 7231540 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2131. Min Range: -9.2131
Max Act: 8.9631. Min Act: -0.1700
Data Index: 5104689 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2131. Min Range: -9.2131
Max Act: 8.9631. Min Act: -0.1700
Data Index: 4276668 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2131. Min Range: -9.2131
Max Act: 8.9631. Min Act: -0.1700
Data Index: 7231545 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2131. Min Range: -9.2131
Max Act: 8.9631. Min Act: -0.1700
Data Index: 2400798 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2131. Min Range: -9.2131
Max Act: 8.9006. Min Act: -0.1700
Data Index: 7141758 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2131. Min Range: -9.2131
Max Act: 8.9006. Min Act: -0.1700
Data Index: 2762078 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2131. Min Range: -9.2131
Max Act: 8.8381. Min Act: -0.1700
Data Index: 2996756 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2131. Min Range: -9.2131
Max Act: 8.9006. Min Act: -0.1700
Data Index: 7207978 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2131. Min Range: -9.2131
Max Act: 8.9006. Min Act: -0.1700
Data Index: 7207979 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2131. Min Range: -9.2131
Max Act: 8.9006. Min Act: -0.1700
Data Index: 7471239 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2131. Min Range: -9.2131
Max Act: 8.8381. Min Act: -0.1700
Data Index: 1547065 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2131. Min Range: -9.2131
Max Act: 8.8381. Min Act: -0.1700
Data Index: 4628113 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19