Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2033 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.4696. Min Range: -2.4696
Max Act: 2.4696. Min Act: -0.1700
Data Index: 1503489 (Python Code)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4696. Min Range: -2.4696
Max Act: 2.4208. Min Act: -0.1700
Data Index: 1434090 (Python Code)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4696. Min Range: -2.4696
Max Act: 2.3555. Min Act: -0.1700
Data Index: 1572912 (Python Code)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4696. Min Range: -2.4696
Max Act: 2.3719. Min Act: -0.1700
Data Index: 1539455 (Python Code)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4696. Min Range: -2.4696
Max Act: 2.3391. Min Act: -0.1700
Data Index: 1626461 (Python Code)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4696. Min Range: -2.4696
Max Act: 2.2899. Min Act: -0.1700
Data Index: 1505984 (Python Code)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4696. Min Range: -2.4696
Max Act: 2.2734. Min Act: -0.1700
Data Index: 1361128 (Python Code)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4696. Min Range: -2.4696
Max Act: 2.2734. Min Act: -0.1700
Data Index: 1577913 (Python Code)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4696. Min Range: -2.4696
Max Act: 2.2569. Min Act: -0.1700
Data Index: 1394205 (Python Code)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4696. Min Range: -2.4696
Max Act: 2.2569. Min Act: -0.1700
Data Index: 1603515 (Python Code)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4696. Min Range: -2.4696
Max Act: 2.2404. Min Act: -0.1700
Data Index: 1560905 (Python Code)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4696. Min Range: -2.4696
Max Act: 2.2404. Min Act: -0.1700
Data Index: 1525573 (Python Code)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4696. Min Range: -2.4696
Max Act: 2.2404. Min Act: -0.1700
Data Index: 1557573 (Python Code)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4696. Min Range: -2.4696
Max Act: 2.2073. Min Act: -0.1700
Data Index: 1399778 (Python Code)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4696. Min Range: -2.4696
Max Act: 2.2073. Min Act: -0.1700
Data Index: 1452474 (Python Code)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4696. Min Range: -2.4696
Max Act: 2.2239. Min Act: -0.1700
Data Index: 1641821 (Python Code)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4696. Min Range: -2.4696
Max Act: 2.2239. Min Act: -0.1700
Data Index: 1370523 (Python Code)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4696. Min Range: -2.4696
Max Act: 2.2239. Min Act: -0.1700
Data Index: 989524 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4696. Min Range: -2.4696
Max Act: 2.2073. Min Act: -0.1700
Data Index: 1452084 (Python Code)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4696. Min Range: -2.4696
Max Act: 2.2073. Min Act: -0.1700
Data Index: 1555285 (Python Code)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19