Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1901 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.7825. Min Range: -4.7825
Max Act: 4.7512. Min Act: -0.1699
Data Index: 1566561 (Python Code)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7825. Min Range: -4.7825
Max Act: 4.7200. Min Act: -0.1700
Data Index: 1522686 (Python Code)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7825. Min Range: -4.7825
Max Act: 4.7200. Min Act: -0.1700
Data Index: 1370795 (Python Code)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7825. Min Range: -4.7825
Max Act: 4.7825. Min Act: -0.1700
Data Index: 1359934 (Python Code)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7825. Min Range: -4.7825
Max Act: 4.6887. Min Act: -0.1700
Data Index: 1653424 (Python Code)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7825. Min Range: -4.7825
Max Act: 4.6887. Min Act: -0.1699
Data Index: 1448137 (Python Code)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7825. Min Range: -4.7825
Max Act: 4.6887. Min Act: -0.1700
Data Index: 1571828 (Python Code)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7825. Min Range: -4.7825
Max Act: 4.6575. Min Act: -0.1700
Data Index: 1601634 (Python Code)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7825. Min Range: -4.7825
Max Act: 4.5950. Min Act: -0.1700
Data Index: 1389236 (Python Code)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7825. Min Range: -4.7825
Max Act: 4.6262. Min Act: -0.1700
Data Index: 1523860 (Python Code)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7825. Min Range: -4.7825
Max Act: 4.5950. Min Act: -0.1700
Data Index: 1609966 (Python Code)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7825. Min Range: -4.7825
Max Act: 4.5637. Min Act: -0.1699
Data Index: 1495747 (Python Code)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7825. Min Range: -4.7825
Max Act: 4.4856. Min Act: -0.1699
Data Index: 1434117 (Python Code)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7825. Min Range: -4.7825
Max Act: 4.5794. Min Act: -0.1700
Data Index: 1532462 (Python Code)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7825. Min Range: -4.7825
Max Act: 4.5481. Min Act: -0.1700
Data Index: 1391920 (Python Code)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7825. Min Range: -4.7825
Max Act: 4.4700. Min Act: -0.1700
Data Index: 1647993 (Python Code)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7825. Min Range: -4.7825
Max Act: 4.4700. Min Act: -0.1699
Data Index: 1418448 (Python Code)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7825. Min Range: -4.7825
Max Act: 4.4856. Min Act: -0.1700
Data Index: 1563372 (Python Code)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7825. Min Range: -4.7825
Max Act: 4.5169. Min Act: -0.1699
Data Index: 1612356 (Python Code)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7825. Min Range: -4.7825
Max Act: 4.4856. Min Act: -0.1662
Data Index: 1605101 (Python Code)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19