Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 809 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.6612. Min Range: -4.6612
Max Act: 4.6612. Min Act: -0.1700
Data Index: 595864 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6612. Min Range: -4.6612
Max Act: 4.6612. Min Act: -0.1700
Data Index: 1037667 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6612. Min Range: -4.6612
Max Act: 4.6612. Min Act: -0.1700
Data Index: 1184284 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6612. Min Range: -4.6612
Max Act: 4.5987. Min Act: -0.1700
Data Index: 247686 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6612. Min Range: -4.6612
Max Act: 4.5362. Min Act: -0.1700
Data Index: 755811 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6612. Min Range: -4.6612
Max Act: 4.4737. Min Act: -0.1700
Data Index: 1130395 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6612. Min Range: -4.6612
Max Act: 4.4737. Min Act: -0.1700
Data Index: 489315 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6612. Min Range: -4.6612
Max Act: 4.4737. Min Act: -0.1700
Data Index: 375453 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6612. Min Range: -4.6612
Max Act: 4.4112. Min Act: -0.1700
Data Index: 209237 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6612. Min Range: -4.6612
Max Act: 4.4425. Min Act: -0.1700
Data Index: 682971 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6612. Min Range: -4.6612
Max Act: 4.4425. Min Act: -0.1700
Data Index: 1335176 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6612. Min Range: -4.6612
Max Act: 4.4425. Min Act: -0.1700
Data Index: 907350 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6612. Min Range: -4.6612
Max Act: 4.4112. Min Act: -0.1700
Data Index: 1281041 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6612. Min Range: -4.6612
Max Act: 4.4425. Min Act: -0.1700
Data Index: 277157 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6612. Min Range: -4.6612
Max Act: 4.3800. Min Act: -0.1700
Data Index: 624435 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6612. Min Range: -4.6612
Max Act: 4.4425. Min Act: -0.1700
Data Index: 607723 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6612. Min Range: -4.6612
Max Act: 4.4425. Min Act: -0.1700
Data Index: 1080809 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6612. Min Range: -4.6612
Max Act: 4.4425. Min Act: -0.1700
Data Index: 993604 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6612. Min Range: -4.6612
Max Act: 4.4112. Min Act: -0.1700
Data Index: 166822 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6612. Min Range: -4.6612
Max Act: 4.4425. Min Act: -0.1700
Data Index: 1256383 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19