Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1074 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.8843. Min Act: -0.1700
Data Index: 931980 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.8843. Min Act: -0.1700
Data Index: 1613060 (Python Code)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.9156. Min Act: -0.1700
Data Index: 1432514 (Python Code)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.7281. Min Act: -0.1700
Data Index: 1400311 (Python Code)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.6968. Min Act: -0.1696
Data Index: 1074029 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.6812. Min Act: -0.1699
Data Index: 994657 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.6031. Min Act: -0.1700
Data Index: 110461 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.5874. Min Act: -0.1700
Data Index: 1497350 (Python Code)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.5874. Min Act: -0.1700
Data Index: 1595905 (Python Code)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.5874. Min Act: -0.1700
Data Index: 1510999 (Python Code)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.5874. Min Act: -0.1699
Data Index: 333037 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.6031. Min Act: -0.1700
Data Index: 529310 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.5405. Min Act: -0.1700
Data Index: 1517254 (Python Code)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.5405. Min Act: -0.1700
Data Index: 1579974 (Python Code)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.5718. Min Act: -0.1700
Data Index: 1591183 (Python Code)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.5405. Min Act: -0.1700
Data Index: 1606448 (Python Code)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.5093. Min Act: -0.1700
Data Index: 1372113 (Python Code)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.4937. Min Act: -0.1700
Data Index: 1586469 (Python Code)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.5093. Min Act: -0.1700
Data Index: 1438798 (Python Code)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9156. Min Range: -4.9156
Max Act: 4.5093. Min Act: -0.1700
Data Index: 1101221 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19