Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 906 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.5087. Min Range: -2.5087
Max Act: 2.5087. Min Act: -0.1700
Data Index: 856279 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5087. Min Range: -2.5087
Max Act: 2.4925. Min Act: -0.1700
Data Index: 1237123 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5087. Min Range: -2.5087
Max Act: 2.5087. Min Act: -0.1700
Data Index: 282201 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5087. Min Range: -2.5087
Max Act: 2.4925. Min Act: -0.1700
Data Index: 535242 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5087. Min Range: -2.5087
Max Act: 2.4925. Min Act: -0.1700
Data Index: 116966 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5087. Min Range: -2.5087
Max Act: 2.4925. Min Act: -0.1700
Data Index: 329382 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5087. Min Range: -2.5087
Max Act: 2.4600. Min Act: -0.1700
Data Index: 440893 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5087. Min Range: -2.5087
Max Act: 2.4275. Min Act: -0.1700
Data Index: 26119 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5087. Min Range: -2.5087
Max Act: 2.4275. Min Act: -0.1700
Data Index: 691474 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5087. Min Range: -2.5087
Max Act: 2.4438. Min Act: -0.1700
Data Index: 975729 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5087. Min Range: -2.5087
Max Act: 2.4438. Min Act: -0.1700
Data Index: 955946 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5087. Min Range: -2.5087
Max Act: 2.4275. Min Act: -0.1700
Data Index: 591590 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5087. Min Range: -2.5087
Max Act: 2.3949. Min Act: -0.1700
Data Index: 426330 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5087. Min Range: -2.5087
Max Act: 2.4275. Min Act: -0.1700
Data Index: 175681 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5087. Min Range: -2.5087
Max Act: 2.4112. Min Act: -0.1700
Data Index: 241718 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5087. Min Range: -2.5087
Max Act: 2.4275. Min Act: -0.1700
Data Index: 1193547 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5087. Min Range: -2.5087
Max Act: 2.4275. Min Act: -0.1700
Data Index: 133387 (C4 (Web Text))
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5087. Min Range: -2.5087
Max Act: 2.4112. Min Act: -0.1700
Data Index: 1076611 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5087. Min Range: -2.5087
Max Act: 2.4275. Min Act: -0.1700
Data Index: 597133 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5087. Min Range: -2.5087
Max Act: 2.4275. Min Act: -0.1700
Data Index: 1060251 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19