Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1868 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3085. Min Range: -4.3085
Max Act: 4.3085. Min Act: -0.1700
Data Index: 1499195 (Python Code)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3085. Min Range: -4.3085
Max Act: 4.3085. Min Act: -0.1700
Data Index: 1439791 (Python Code)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3085. Min Range: -4.3085
Max Act: 4.2773. Min Act: -0.1700
Data Index: 1481001 (Python Code)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3085. Min Range: -4.3085
Max Act: 4.2773. Min Act: -0.1700
Data Index: 1370695 (Python Code)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3085. Min Range: -4.3085
Max Act: 4.2773. Min Act: -0.1700
Data Index: 1364748 (Python Code)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3085. Min Range: -4.3085
Max Act: 4.2460. Min Act: -0.1700
Data Index: 1481026 (Python Code)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3085. Min Range: -4.3085
Max Act: 4.2460. Min Act: -0.1700
Data Index: 1548344 (Python Code)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3085. Min Range: -4.3085
Max Act: 4.2460. Min Act: -0.1700
Data Index: 1572293 (Python Code)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3085. Min Range: -4.3085
Max Act: 4.2773. Min Act: -0.1700
Data Index: 1387936 (Python Code)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3085. Min Range: -4.3085
Max Act: 4.2147. Min Act: -0.1700
Data Index: 1488554 (Python Code)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3085. Min Range: -4.3085
Max Act: 4.2460. Min Act: -0.1700
Data Index: 1414940 (Python Code)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3085. Min Range: -4.3085
Max Act: 4.2147. Min Act: -0.1700
Data Index: 1394303 (Python Code)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3085. Min Range: -4.3085
Max Act: 4.2460. Min Act: -0.1700
Data Index: 1497326 (Python Code)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3085. Min Range: -4.3085
Max Act: 4.1835. Min Act: -0.1700
Data Index: 1459308 (Python Code)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3085. Min Range: -4.3085
Max Act: 4.2147. Min Act: -0.1700
Data Index: 1454580 (Python Code)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3085. Min Range: -4.3085
Max Act: 4.2460. Min Act: -0.1700
Data Index: 1448201 (Python Code)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3085. Min Range: -4.3085
Max Act: 4.2147. Min Act: -0.1700
Data Index: 1653624 (Python Code)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3085. Min Range: -4.3085
Max Act: 4.1835. Min Act: -0.1700
Data Index: 1480265 (Python Code)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3085. Min Range: -4.3085
Max Act: 4.1522. Min Act: -0.1700
Data Index: 1487887 (Python Code)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3085. Min Range: -4.3085
Max Act: 4.1522. Min Act: -0.1700
Data Index: 1375365 (Python Code)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #19