Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 824 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7527. Min Range: -2.7527
Max Act: 2.7527. Min Act: -0.1700
Data Index: 1511478 (Python Code)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7527. Min Range: -2.7527
Max Act: 2.7048. Min Act: -0.1700
Data Index: 1458147 (Python Code)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7527. Min Range: -2.7527
Max Act: 2.6888. Min Act: -0.1700
Data Index: 1375329 (Python Code)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7527. Min Range: -2.7527
Max Act: 2.6727. Min Act: -0.1700
Data Index: 1502689 (Python Code)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7527. Min Range: -2.7527
Max Act: 2.6727. Min Act: -0.1700
Data Index: 1443190 (Python Code)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7527. Min Range: -2.7527
Max Act: 2.6567. Min Act: -0.1700
Data Index: 1369443 (Python Code)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7527. Min Range: -2.7527
Max Act: 2.6407. Min Act: -0.1700
Data Index: 1403077 (Python Code)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7527. Min Range: -2.7527
Max Act: 2.6567. Min Act: -0.1700
Data Index: 1582841 (Python Code)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7527. Min Range: -2.7527
Max Act: 2.6567. Min Act: -0.1700
Data Index: 1423375 (Python Code)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7527. Min Range: -2.7527
Max Act: 2.6407. Min Act: -0.1700
Data Index: 1388840 (Python Code)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7527. Min Range: -2.7527
Max Act: 2.6567. Min Act: -0.1700
Data Index: 1544561 (Python Code)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7527. Min Range: -2.7527
Max Act: 2.6567. Min Act: -0.1700
Data Index: 1481213 (Python Code)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7527. Min Range: -2.7527
Max Act: 2.6567. Min Act: -0.1700
Data Index: 1377802 (Python Code)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7527. Min Range: -2.7527
Max Act: 2.6567. Min Act: -0.1700
Data Index: 781254 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7527. Min Range: -2.7527
Max Act: 2.6407. Min Act: -0.1700
Data Index: 1480872 (Python Code)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7527. Min Range: -2.7527
Max Act: 2.6567. Min Act: -0.1700
Data Index: 1478685 (Python Code)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7527. Min Range: -2.7527
Max Act: 2.6407. Min Act: -0.1700
Data Index: 1461018 (Python Code)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7527. Min Range: -2.7527
Max Act: 2.6407. Min Act: -0.1700
Data Index: 1461067 (Python Code)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7527. Min Range: -2.7527
Max Act: 2.6407. Min Act: -0.1700
Data Index: 1430784 (Python Code)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7527. Min Range: -2.7527
Max Act: 2.6246. Min Act: -0.1700
Data Index: 1475646 (Python Code)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19