Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1856 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5668. Min Range: -2.5668
Max Act: 2.5668. Min Act: -0.1700
Data Index: 885385 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5668. Min Range: -2.5668
Max Act: 2.5507. Min Act: -0.1700
Data Index: 1559388 (Python Code)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5668. Min Range: -2.5668
Max Act: 2.5022. Min Act: -0.1700
Data Index: 1049234 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5668. Min Range: -2.5668
Max Act: 2.5022. Min Act: -0.1700
Data Index: 1539299 (Python Code)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5668. Min Range: -2.5668
Max Act: 2.4860. Min Act: -0.1700
Data Index: 1385679 (Python Code)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5668. Min Range: -2.5668
Max Act: 2.4372. Min Act: -0.1700
Data Index: 1519814 (Python Code)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5668. Min Range: -2.5668
Max Act: 2.4535. Min Act: -0.1700
Data Index: 1466450 (Python Code)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5668. Min Range: -2.5668
Max Act: 2.4372. Min Act: -0.1700
Data Index: 1338648 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5668. Min Range: -2.5668
Max Act: 2.4210. Min Act: -0.1700
Data Index: 1529874 (Python Code)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5668. Min Range: -2.5668
Max Act: 2.4210. Min Act: -0.1700
Data Index: 1648037 (Python Code)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5668. Min Range: -2.5668
Max Act: 2.4210. Min Act: -0.1700
Data Index: 1390156 (Python Code)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5668. Min Range: -2.5668
Max Act: 2.4047. Min Act: -0.1700
Data Index: 1364665 (Python Code)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5668. Min Range: -2.5668
Max Act: 2.4210. Min Act: -0.1700
Data Index: 1437863 (Python Code)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5668. Min Range: -2.5668
Max Act: 2.3884. Min Act: -0.1700
Data Index: 1034725 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5668. Min Range: -2.5668
Max Act: 2.3884. Min Act: -0.1700
Data Index: 1509941 (Python Code)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5668. Min Range: -2.5668
Max Act: 2.3884. Min Act: -0.1700
Data Index: 1503329 (Python Code)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5668. Min Range: -2.5668
Max Act: 2.3884. Min Act: -0.1700
Data Index: 1458586 (Python Code)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5668. Min Range: -2.5668
Max Act: 2.3884. Min Act: -0.1700
Data Index: 1429270 (Python Code)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5668. Min Range: -2.5668
Max Act: 2.3884. Min Act: -0.1700
Data Index: 1609819 (Python Code)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5668. Min Range: -2.5668
Max Act: 2.3884. Min Act: -0.1700
Data Index: 1643296 (Python Code)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19