Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1083 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7741. Min Range: -2.7741
Max Act: 2.7741. Min Act: -0.1700
Data Index: 747898 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7741. Min Range: -2.7741
Max Act: 2.7262. Min Act: -0.1700
Data Index: 1642321 (Python Code)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7741. Min Range: -2.7741
Max Act: 2.6461. Min Act: -0.1700
Data Index: 1417274 (Python Code)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7741. Min Range: -2.7741
Max Act: 2.6461. Min Act: -0.1700
Data Index: 1384641 (Python Code)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7741. Min Range: -2.7741
Max Act: 2.5495. Min Act: -0.1700
Data Index: 1314685 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7741. Min Range: -2.7741
Max Act: 2.5818. Min Act: -0.1700
Data Index: 1585743 (Python Code)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7741. Min Range: -2.7741
Max Act: 2.5657. Min Act: -0.1700
Data Index: 35611 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7741. Min Range: -2.7741
Max Act: 2.5334. Min Act: -0.1700
Data Index: 1654268 (Python Code)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7741. Min Range: -2.7741
Max Act: 2.5657. Min Act: -0.1700
Data Index: 1528247 (Python Code)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7741. Min Range: -2.7741
Max Act: 2.5657. Min Act: -0.1700
Data Index: 1575305 (Python Code)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7741. Min Range: -2.7741
Max Act: 2.5495. Min Act: -0.1700
Data Index: 1480817 (Python Code)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7741. Min Range: -2.7741
Max Act: 2.5495. Min Act: -0.1700
Data Index: 327374 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7741. Min Range: -2.7741
Max Act: 2.5334. Min Act: -0.1700
Data Index: 1206424 (C4 (Web Text))
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7741. Min Range: -2.7741
Max Act: 2.5495. Min Act: -0.1700
Data Index: 1367224 (Python Code)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7741. Min Range: -2.7741
Max Act: 2.5172. Min Act: -0.1700
Data Index: 156888 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7741. Min Range: -2.7741
Max Act: 2.5334. Min Act: -0.1700
Data Index: 1383768 (Python Code)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7741. Min Range: -2.7741
Max Act: 2.5495. Min Act: -0.1700
Data Index: 1389806 (Python Code)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7741. Min Range: -2.7741
Max Act: 2.5334. Min Act: -0.1700
Data Index: 1398992 (Python Code)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7741. Min Range: -2.7741
Max Act: 2.5172. Min Act: -0.1700
Data Index: 1634876 (Python Code)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7741. Min Range: -2.7741
Max Act: 2.5334. Min Act: -0.1700
Data Index: 1609330 (Python Code)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19