Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 251 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.1832. Min Range: -5.1832
Max Act: 5.1832. Min Act: -0.1700
Data Index: 1229375 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1832. Min Range: -5.1832
Max Act: 4.9957. Min Act: -0.1700
Data Index: 713271 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1832. Min Range: -5.1832
Max Act: 4.8082. Min Act: -0.1700
Data Index: 780350 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1832. Min Range: -5.1832
Max Act: 4.7145. Min Act: -0.1700
Data Index: 864652 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1832. Min Range: -5.1832
Max Act: 4.6832. Min Act: -0.1700
Data Index: 385837 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1832. Min Range: -5.1832
Max Act: 4.6832. Min Act: -0.1700
Data Index: 1048820 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1832. Min Range: -5.1832
Max Act: 4.6520. Min Act: -0.1700
Data Index: 241551 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1832. Min Range: -5.1832
Max Act: 4.6207. Min Act: -0.1700
Data Index: 1304346 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1832. Min Range: -5.1832
Max Act: 4.5895. Min Act: -0.1700
Data Index: 315891 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1832. Min Range: -5.1832
Max Act: 4.6207. Min Act: -0.1700
Data Index: 555823 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1832. Min Range: -5.1832
Max Act: 4.5582. Min Act: -0.1700
Data Index: 1077512 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1832. Min Range: -5.1832
Max Act: 4.6207. Min Act: -0.1700
Data Index: 997811 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1832. Min Range: -5.1832
Max Act: 4.6520. Min Act: -0.1700
Data Index: 638014 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1832. Min Range: -5.1832
Max Act: 4.6207. Min Act: -0.1700
Data Index: 728568 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1832. Min Range: -5.1832
Max Act: 4.5582. Min Act: -0.1700
Data Index: 752769 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1832. Min Range: -5.1832
Max Act: 4.6207. Min Act: -0.1700
Data Index: 827893 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1832. Min Range: -5.1832
Max Act: 4.6207. Min Act: -0.1700
Data Index: 511786 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1832. Min Range: -5.1832
Max Act: 4.5270. Min Act: -0.1700
Data Index: 432126 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1832. Min Range: -5.1832
Max Act: 4.5895. Min Act: -0.1700
Data Index: 784974 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1832. Min Range: -5.1832
Max Act: 4.5582. Min Act: -0.1700
Data Index: 1004939 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19