Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1300 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2901. Min Range: -4.2901
Max Act: 4.2901. Min Act: -0.1700
Data Index: 1394645 (Python Code)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2901. Min Range: -4.2901
Max Act: 4.2901. Min Act: -0.1700
Data Index: 1651192 (Python Code)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2901. Min Range: -4.2901
Max Act: 4.2276. Min Act: -0.1700
Data Index: 1554012 (Python Code)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2901. Min Range: -4.2901
Max Act: 4.2276. Min Act: -0.1700
Data Index: 1517701 (Python Code)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2901. Min Range: -4.2901
Max Act: 4.1026. Min Act: -0.1700
Data Index: 1567834 (Python Code)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2901. Min Range: -4.2901
Max Act: 4.1026. Min Act: -0.1700
Data Index: 1604195 (Python Code)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2901. Min Range: -4.2901
Max Act: 4.0400. Min Act: -0.1700
Data Index: 1363759 (Python Code)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2901. Min Range: -4.2901
Max Act: 4.0400. Min Act: -0.1700
Data Index: 1655892 (Python Code)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2901. Min Range: -4.2901
Max Act: 4.1026. Min Act: -0.1700
Data Index: 1581136 (Python Code)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2901. Min Range: -4.2901
Max Act: 4.0088. Min Act: -0.1700
Data Index: 1495698 (Python Code)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2901. Min Range: -4.2901
Max Act: 4.0088. Min Act: -0.1700
Data Index: 1480697 (Python Code)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2901. Min Range: -4.2901
Max Act: 3.9462. Min Act: -0.1700
Data Index: 1425245 (Python Code)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2901. Min Range: -4.2901
Max Act: 3.9462. Min Act: -0.1700
Data Index: 1518839 (Python Code)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2901. Min Range: -4.2901
Max Act: 3.8993. Min Act: -0.1700
Data Index: 1426636 (Python Code)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2901. Min Range: -4.2901
Max Act: 3.9150. Min Act: -0.1700
Data Index: 1418880 (Python Code)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2901. Min Range: -4.2901
Max Act: 3.9150. Min Act: -0.1700
Data Index: 1491613 (Python Code)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2901. Min Range: -4.2901
Max Act: 3.9775. Min Act: -0.1700
Data Index: 1531985 (Python Code)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2901. Min Range: -4.2901
Max Act: 3.9150. Min Act: -0.1700
Data Index: 1472092 (Python Code)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2901. Min Range: -4.2901
Max Act: 3.8837. Min Act: -0.1700
Data Index: 1581900 (Python Code)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2901. Min Range: -4.2901
Max Act: 3.9150. Min Act: -0.1700
Data Index: 1467053 (Python Code)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #19