Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1971 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5048. Min Range: -2.5048
Max Act: 2.5048. Min Act: -0.1700
Data Index: 1039006 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5048. Min Range: -2.5048
Max Act: 2.4399. Min Act: -0.1700
Data Index: 280641 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5048. Min Range: -2.5048
Max Act: 2.3910. Min Act: -0.1700
Data Index: 717662 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5048. Min Range: -2.5048
Max Act: 2.3910. Min Act: -0.1700
Data Index: 435204 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5048. Min Range: -2.5048
Max Act: 2.3747. Min Act: -0.1700
Data Index: 480899 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5048. Min Range: -2.5048
Max Act: 2.3910. Min Act: -0.1700
Data Index: 761600 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5048. Min Range: -2.5048
Max Act: 2.3583. Min Act: -0.1700
Data Index: 614393 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5048. Min Range: -2.5048
Max Act: 2.3583. Min Act: -0.1700
Data Index: 835727 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5048. Min Range: -2.5048
Max Act: 2.3583. Min Act: -0.1700
Data Index: 475679 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5048. Min Range: -2.5048
Max Act: 2.3583. Min Act: -0.1700
Data Index: 203399 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5048. Min Range: -2.5048
Max Act: 2.3420. Min Act: -0.1700
Data Index: 165118 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5048. Min Range: -2.5048
Max Act: 2.3256. Min Act: -0.1700
Data Index: 160273 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5048. Min Range: -2.5048
Max Act: 2.3092. Min Act: -0.1700
Data Index: 820071 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5048. Min Range: -2.5048
Max Act: 2.3256. Min Act: -0.1700
Data Index: 493715 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5048. Min Range: -2.5048
Max Act: 2.3092. Min Act: -0.1700
Data Index: 535581 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5048. Min Range: -2.5048
Max Act: 2.3256. Min Act: -0.1700
Data Index: 129740 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5048. Min Range: -2.5048
Max Act: 2.3092. Min Act: -0.1700
Data Index: 266761 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5048. Min Range: -2.5048
Max Act: 2.3092. Min Act: -0.1700
Data Index: 22873 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5048. Min Range: -2.5048
Max Act: 2.3256. Min Act: -0.1700
Data Index: 708088 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5048. Min Range: -2.5048
Max Act: 2.3092. Min Act: -0.1700
Data Index: 642225 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19