Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3567 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4696. Min Range: -6.4696
Max Act: 6.4696. Min Act: -0.1700
Data Index: 4079090 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4696. Min Range: -6.4696
Max Act: 6.3759. Min Act: -0.1700
Data Index: 2357112 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4696. Min Range: -6.4696
Max Act: 6.3759. Min Act: -0.1700
Data Index: 3904769 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4696. Min Range: -6.4696
Max Act: 6.1884. Min Act: -0.1700
Data Index: 6194543 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4696. Min Range: -6.4696
Max Act: 6.1571. Min Act: -0.1700
Data Index: 3850044 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4696. Min Range: -6.4696
Max Act: 6.1259. Min Act: -0.1700
Data Index: 595594 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4696. Min Range: -6.4696
Max Act: 6.0634. Min Act: -0.1700
Data Index: 6538515 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4696. Min Range: -6.4696
Max Act: 6.0634. Min Act: -0.1700
Data Index: 2755865 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4696. Min Range: -6.4696
Max Act: 5.9071. Min Act: -0.1700
Data Index: 3536552 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4696. Min Range: -6.4696
Max Act: 5.9071. Min Act: -0.1699
Data Index: 5118853 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4696. Min Range: -6.4696
Max Act: 5.8446. Min Act: -0.1700
Data Index: 950428 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4696. Min Range: -6.4696
Max Act: 5.8759. Min Act: -0.1700
Data Index: 4050060 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4696. Min Range: -6.4696
Max Act: 5.8134. Min Act: -0.1700
Data Index: 1820273 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4696. Min Range: -6.4696
Max Act: 5.7821. Min Act: -0.1700
Data Index: 6194544 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4696. Min Range: -6.4696
Max Act: 5.7821. Min Act: -0.1700
Data Index: 6335901 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4696. Min Range: -6.4696
Max Act: 5.7821. Min Act: -0.1700
Data Index: 2322178 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4696. Min Range: -6.4696
Max Act: 5.7509. Min Act: -0.1700
Data Index: 2158898 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4696. Min Range: -6.4696
Max Act: 5.7509. Min Act: -0.1700
Data Index: 5695940 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4696. Min Range: -6.4696
Max Act: 5.7196. Min Act: -0.1700
Data Index: 4753953 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4696. Min Range: -6.4696
Max Act: 5.7509. Min Act: -0.1700
Data Index: 4747026 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19