Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 423 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 8.1666. Min Range: -8.1666
Max Act: 8.1666. Min Act: -0.1700
Data Index: 1481190 (Python Code)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1666. Min Range: -8.1666
Max Act: 8.0416. Min Act: -0.1700
Data Index: 1620923 (Python Code)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1666. Min Range: -8.1666
Max Act: 8.0416. Min Act: -0.1700
Data Index: 1504325 (Python Code)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1666. Min Range: -8.1666
Max Act: 8.1354. Min Act: -0.1700
Data Index: 1436410 (Python Code)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1666. Min Range: -8.1666
Max Act: 8.0104. Min Act: -0.1700
Data Index: 980691 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1666. Min Range: -8.1666
Max Act: 8.0729. Min Act: -0.1700
Data Index: 860959 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1666. Min Range: -8.1666
Max Act: 7.9479. Min Act: -0.1700
Data Index: 1351253 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1666. Min Range: -8.1666
Max Act: 8.0416. Min Act: -0.1700
Data Index: 282990 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1666. Min Range: -8.1666
Max Act: 7.9791. Min Act: -0.1700
Data Index: 765727 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1666. Min Range: -8.1666
Max Act: 7.9791. Min Act: -0.1700
Data Index: 1050559 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1666. Min Range: -8.1666
Max Act: 8.0104. Min Act: -0.1700
Data Index: 1476605 (Python Code)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1666. Min Range: -8.1666
Max Act: 8.0104. Min Act: -0.1700
Data Index: 1513923 (Python Code)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1666. Min Range: -8.1666
Max Act: 7.9791. Min Act: -0.1700
Data Index: 1622489 (Python Code)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1666. Min Range: -8.1666
Max Act: 7.9479. Min Act: -0.1699
Data Index: 1102313 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1666. Min Range: -8.1666
Max Act: 7.8854. Min Act: -0.1700
Data Index: 1521071 (Python Code)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1666. Min Range: -8.1666
Max Act: 7.7916. Min Act: -0.1700
Data Index: 1392172 (Python Code)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1666. Min Range: -8.1666
Max Act: 7.8229. Min Act: -0.1700
Data Index: 1527493 (Python Code)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1666. Min Range: -8.1666
Max Act: 7.9166. Min Act: -0.1700
Data Index: 1550642 (Python Code)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1666. Min Range: -8.1666
Max Act: 7.9479. Min Act: -0.1700
Data Index: 463050 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1666. Min Range: -8.1666
Max Act: 7.8541. Min Act: -0.1700
Data Index: 1532186 (Python Code)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19