Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 732 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 6.4998. Min Range: -6.4998
Max Act: 6.4998. Min Act: -0.1700
Data Index: 1390972 (Python Code)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4998. Min Range: -6.4998
Max Act: 6.3436. Min Act: -0.1700
Data Index: 1596090 (Python Code)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4998. Min Range: -6.4998
Max Act: 6.3436. Min Act: -0.1700
Data Index: 1577109 (Python Code)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4998. Min Range: -6.4998
Max Act: 6.2811. Min Act: -0.1700
Data Index: 1590258 (Python Code)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4998. Min Range: -6.4998
Max Act: 6.2498. Min Act: -0.1700
Data Index: 1561529 (Python Code)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4998. Min Range: -6.4998
Max Act: 6.2811. Min Act: -0.1700
Data Index: 459501 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4998. Min Range: -6.4998
Max Act: 6.2186. Min Act: -0.1700
Data Index: 1520945 (Python Code)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4998. Min Range: -6.4998
Max Act: 6.2498. Min Act: -0.1700
Data Index: 1432348 (Python Code)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4998. Min Range: -6.4998
Max Act: 6.1873. Min Act: -0.1700
Data Index: 1366934 (Python Code)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4998. Min Range: -6.4998
Max Act: 6.1873. Min Act: -0.1700
Data Index: 1485571 (Python Code)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4998. Min Range: -6.4998
Max Act: 6.1561. Min Act: -0.1700
Data Index: 1384648 (Python Code)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4998. Min Range: -6.4998
Max Act: 6.1873. Min Act: -0.1700
Data Index: 1484292 (Python Code)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4998. Min Range: -6.4998
Max Act: 6.1561. Min Act: -0.1700
Data Index: 1426068 (Python Code)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4998. Min Range: -6.4998
Max Act: 6.1561. Min Act: -0.1700
Data Index: 1469787 (Python Code)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4998. Min Range: -6.4998
Max Act: 6.1873. Min Act: -0.1700
Data Index: 1466941 (Python Code)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4998. Min Range: -6.4998
Max Act: 6.1248. Min Act: -0.1700
Data Index: 1367077 (Python Code)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4998. Min Range: -6.4998
Max Act: 6.1248. Min Act: -0.1700
Data Index: 1360057 (Python Code)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4998. Min Range: -6.4998
Max Act: 6.0936. Min Act: -0.1700
Data Index: 1376407 (Python Code)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4998. Min Range: -6.4998
Max Act: 5.9998. Min Act: -0.1700
Data Index: 1615869 (Python Code)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4998. Min Range: -6.4998
Max Act: 6.2186. Min Act: -0.1700
Data Index: 1600154 (Python Code)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19