Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1201 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 6.1832. Min Range: -6.1832
Max Act: 6.1832. Min Act: -0.1700
Data Index: 604466 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1832. Min Range: -6.1832
Max Act: 6.0269. Min Act: -0.1700
Data Index: 711807 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1832. Min Range: -6.1832
Max Act: 5.5894. Min Act: -0.1700
Data Index: 749312 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1832. Min Range: -6.1832
Max Act: 5.5582. Min Act: -0.1700
Data Index: 1279415 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1832. Min Range: -6.1832
Max Act: 5.5582. Min Act: -0.1700
Data Index: 258893 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1832. Min Range: -6.1832
Max Act: 5.5582. Min Act: -0.1700
Data Index: 942438 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1832. Min Range: -6.1832
Max Act: 5.5269. Min Act: -0.1700
Data Index: 47373 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1832. Min Range: -6.1832
Max Act: 5.4644. Min Act: -0.1700
Data Index: 46613 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1832. Min Range: -6.1832
Max Act: 5.5894. Min Act: -0.1700
Data Index: 1305204 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1832. Min Range: -6.1832
Max Act: 5.4957. Min Act: -0.1700
Data Index: 1063454 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1832. Min Range: -6.1832
Max Act: 5.4019. Min Act: -0.1700
Data Index: 1295831 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1832. Min Range: -6.1832
Max Act: 5.4957. Min Act: -0.1700
Data Index: 1440276 (Python Code)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1832. Min Range: -6.1832
Max Act: 5.3707. Min Act: -0.1700
Data Index: 1123335 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1832. Min Range: -6.1832
Max Act: 5.4019. Min Act: -0.1700
Data Index: 950092 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1832. Min Range: -6.1832
Max Act: 5.4644. Min Act: -0.1700
Data Index: 349295 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1832. Min Range: -6.1832
Max Act: 5.4332. Min Act: -0.1700
Data Index: 1050517 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1832. Min Range: -6.1832
Max Act: 5.3707. Min Act: -0.1700
Data Index: 1387967 (Python Code)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1832. Min Range: -6.1832
Max Act: 5.4019. Min Act: -0.1700
Data Index: 885359 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1832. Min Range: -6.1832
Max Act: 5.3707. Min Act: -0.1700
Data Index: 538456 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1832. Min Range: -6.1832
Max Act: 5.3082. Min Act: -0.1700
Data Index: 1136332 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19