Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2024 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.2988. Min Range: -2.2988
Max Act: 2.2988. Min Act: -0.1700
Data Index: 1475921 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2988. Min Range: -2.2988
Max Act: 2.2163. Min Act: -0.1686
Data Index: 1490472 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2988. Min Range: -2.2988
Max Act: 2.2163. Min Act: -0.1699
Data Index: 1638789 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2988. Min Range: -2.2988
Max Act: 2.1832. Min Act: -0.1700
Data Index: 1390549 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2988. Min Range: -2.2988
Max Act: 2.1499. Min Act: -0.1696
Data Index: 1475757 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2988. Min Range: -2.2988
Max Act: 2.1332. Min Act: -0.1698
Data Index: 1446926 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2988. Min Range: -2.2988
Max Act: 2.1165. Min Act: -0.1690
Data Index: 1415908 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2988. Min Range: -2.2988
Max Act: 2.1165. Min Act: -0.1699
Data Index: 1488966 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2988. Min Range: -2.2988
Max Act: 2.0998. Min Act: -0.1700
Data Index: 1622190 (Python Code)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2988. Min Range: -2.2988
Max Act: 2.0831. Min Act: -0.1697
Data Index: 1369637 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2988. Min Range: -2.2988
Max Act: 2.0831. Min Act: -0.1700
Data Index: 1445889 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2988. Min Range: -2.2988
Max Act: 2.0831. Min Act: -0.1698
Data Index: 1508057 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2988. Min Range: -2.2988
Max Act: 2.0998. Min Act: -0.1700
Data Index: 1600367 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2988. Min Range: -2.2988
Max Act: 2.0831. Min Act: -0.1664
Data Index: 1476537 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2988. Min Range: -2.2988
Max Act: 2.0831. Min Act: -0.1693
Data Index: 1537951 (Python Code)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2988. Min Range: -2.2988
Max Act: 2.0663. Min Act: -0.1697
Data Index: 1574590 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2988. Min Range: -2.2988
Max Act: 2.0831. Min Act: -0.1700
Data Index: 1642860 (Python Code)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2988. Min Range: -2.2988
Max Act: 2.0831. Min Act: -0.1700
Data Index: 1464803 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2988. Min Range: -2.2988
Max Act: 2.0663. Min Act: -0.1695
Data Index: 1475216 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2988. Min Range: -2.2988
Max Act: 2.0495. Min Act: -0.1700
Data Index: 1475682 (Python Code)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19