Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1594 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 6.1514. Min Range: -6.1514
Max Act: 6.1514. Min Act: -0.1700
Data Index: 734974 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1514. Min Range: -6.1514
Max Act: 5.9014. Min Act: -0.1700
Data Index: 1644504 (Python Code)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1514. Min Range: -6.1514
Max Act: 5.7452. Min Act: -0.1700
Data Index: 780665 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1514. Min Range: -6.1514
Max Act: 5.5889. Min Act: -0.1700
Data Index: 1316886 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1514. Min Range: -6.1514
Max Act: 5.4327. Min Act: -0.1700
Data Index: 1411428 (Python Code)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1514. Min Range: -6.1514
Max Act: 5.3702. Min Act: -0.1700
Data Index: 837753 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1514. Min Range: -6.1514
Max Act: 5.2139. Min Act: -0.1700
Data Index: 1353086 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1514. Min Range: -6.1514
Max Act: 5.2452. Min Act: -0.1700
Data Index: 212197 (C4 (Web Text))
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1514. Min Range: -6.1514
Max Act: 5.2139. Min Act: -0.1700
Data Index: 592344 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1514. Min Range: -6.1514
Max Act: 5.1827. Min Act: -0.1700
Data Index: 621666 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1514. Min Range: -6.1514
Max Act: 5.1827. Min Act: -0.1700
Data Index: 133543 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1514. Min Range: -6.1514
Max Act: 5.1202. Min Act: -0.1700
Data Index: 700285 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1514. Min Range: -6.1514
Max Act: 5.0889. Min Act: -0.1700
Data Index: 234789 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1514. Min Range: -6.1514
Max Act: 5.0889. Min Act: -0.1700
Data Index: 224661 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1514. Min Range: -6.1514
Max Act: 5.1202. Min Act: -0.1700
Data Index: 648378 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1514. Min Range: -6.1514
Max Act: 5.0577. Min Act: -0.1700
Data Index: 958556 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1514. Min Range: -6.1514
Max Act: 4.9952. Min Act: -0.1700
Data Index: 217061 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1514. Min Range: -6.1514
Max Act: 4.9952. Min Act: -0.1700
Data Index: 926584 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1514. Min Range: -6.1514
Max Act: 4.9952. Min Act: -0.1700
Data Index: 99656 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1514. Min Range: -6.1514
Max Act: 4.9952. Min Act: -0.1700
Data Index: 1461255 (Python Code)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19