Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1960 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0376. Min Range: -4.0376
Max Act: 4.0376. Min Act: -0.1700
Data Index: 1099320 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0376. Min Range: -4.0376
Max Act: 3.9125. Min Act: -0.1700
Data Index: 427120 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0376. Min Range: -4.0376
Max Act: 3.9438. Min Act: -0.1700
Data Index: 952886 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0376. Min Range: -4.0376
Max Act: 3.8499. Min Act: -0.1700
Data Index: 1120482 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0376. Min Range: -4.0376
Max Act: 3.9125. Min Act: -0.1700
Data Index: 153736 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0376. Min Range: -4.0376
Max Act: 3.8812. Min Act: -0.1700
Data Index: 574053 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0376. Min Range: -4.0376
Max Act: 3.8187. Min Act: -0.1700
Data Index: 153854 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0376. Min Range: -4.0376
Max Act: 3.8812. Min Act: -0.1700
Data Index: 111211 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0376. Min Range: -4.0376
Max Act: 3.8187. Min Act: -0.1700
Data Index: 647920 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0376. Min Range: -4.0376
Max Act: 3.7874. Min Act: -0.1700
Data Index: 1029897 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0376. Min Range: -4.0376
Max Act: 3.7874. Min Act: -0.1700
Data Index: 511485 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0376. Min Range: -4.0376
Max Act: 3.7874. Min Act: -0.1700
Data Index: 236034 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0376. Min Range: -4.0376
Max Act: 3.8187. Min Act: -0.1700
Data Index: 438527 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0376. Min Range: -4.0376
Max Act: 3.8499. Min Act: -0.1700
Data Index: 1351219 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0376. Min Range: -4.0376
Max Act: 3.8187. Min Act: -0.1700
Data Index: 1073157 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0376. Min Range: -4.0376
Max Act: 3.8187. Min Act: -0.1700
Data Index: 382263 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0376. Min Range: -4.0376
Max Act: 3.8187. Min Act: -0.1700
Data Index: 143581 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0376. Min Range: -4.0376
Max Act: 3.8187. Min Act: -0.1700
Data Index: 1092089 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0376. Min Range: -4.0376
Max Act: 3.7874. Min Act: -0.1700
Data Index: 135723 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0376. Min Range: -4.0376
Max Act: 3.7561. Min Act: -0.1700
Data Index: 717352 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19