Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 198 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7907. Min Range: -2.7907
Max Act: 2.7907. Min Act: -0.1700
Data Index: 250511 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7907. Min Range: -2.7907
Max Act: 2.7269. Min Act: -0.1700
Data Index: 1516711 (Python Code)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7907. Min Range: -2.7907
Max Act: 2.7109. Min Act: -0.1700
Data Index: 1363263 (Python Code)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7907. Min Range: -2.7907
Max Act: 2.7109. Min Act: -0.1700
Data Index: 1572026 (Python Code)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7907. Min Range: -2.7907
Max Act: 2.6949. Min Act: -0.1700
Data Index: 1608233 (Python Code)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7907. Min Range: -2.7907
Max Act: 2.6949. Min Act: -0.1700
Data Index: 1476930 (Python Code)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7907. Min Range: -2.7907
Max Act: 2.6949. Min Act: -0.1700
Data Index: 1620572 (Python Code)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7907. Min Range: -2.7907
Max Act: 2.6789. Min Act: -0.1700
Data Index: 1498498 (Python Code)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7907. Min Range: -2.7907
Max Act: 2.6629. Min Act: -0.1700
Data Index: 1499399 (Python Code)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7907. Min Range: -2.7907
Max Act: 2.6789. Min Act: -0.1700
Data Index: 1599171 (Python Code)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7907. Min Range: -2.7907
Max Act: 2.6629. Min Act: -0.1700
Data Index: 1637688 (Python Code)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7907. Min Range: -2.7907
Max Act: 2.6629. Min Act: -0.1700
Data Index: 1629930 (Python Code)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7907. Min Range: -2.7907
Max Act: 2.6629. Min Act: -0.1700
Data Index: 1361607 (Python Code)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7907. Min Range: -2.7907
Max Act: 2.6308. Min Act: -0.1700
Data Index: 1364163 (Python Code)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7907. Min Range: -2.7907
Max Act: 2.6629. Min Act: -0.1700
Data Index: 1388902 (Python Code)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7907. Min Range: -2.7907
Max Act: 2.6308. Min Act: -0.1700
Data Index: 1374968 (Python Code)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7907. Min Range: -2.7907
Max Act: 2.6468. Min Act: -0.1700
Data Index: 1544494 (Python Code)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7907. Min Range: -2.7907
Max Act: 2.6308. Min Act: -0.1700
Data Index: 1379815 (Python Code)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7907. Min Range: -2.7907
Max Act: 2.6468. Min Act: -0.1700
Data Index: 1631745 (Python Code)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7907. Min Range: -2.7907
Max Act: 2.6468. Min Act: -0.1700
Data Index: 1621814 (Python Code)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19