Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 893 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.6998. Min Range: -4.6998
Max Act: 4.6998. Min Act: -0.1700
Data Index: 228969 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6998. Min Range: -4.6998
Max Act: 4.6373. Min Act: -0.1700
Data Index: 993272 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6998. Min Range: -4.6998
Max Act: 4.5436. Min Act: -0.1700
Data Index: 840176 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6998. Min Range: -4.6998
Max Act: 4.5436. Min Act: -0.1700
Data Index: 702375 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6998. Min Range: -4.6998
Max Act: 4.4811. Min Act: -0.1700
Data Index: 1165788 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6998. Min Range: -4.6998
Max Act: 4.4811. Min Act: -0.1700
Data Index: 290660 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6998. Min Range: -4.6998
Max Act: 4.4186. Min Act: -0.1700
Data Index: 336122 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6998. Min Range: -4.6998
Max Act: 4.3873. Min Act: -0.1700
Data Index: 176165 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6998. Min Range: -4.6998
Max Act: 4.4186. Min Act: -0.1700
Data Index: 461799 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6998. Min Range: -4.6998
Max Act: 4.4186. Min Act: -0.1700
Data Index: 411880 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6998. Min Range: -4.6998
Max Act: 4.3873. Min Act: -0.1700
Data Index: 329061 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6998. Min Range: -4.6998
Max Act: 4.4186. Min Act: -0.1700
Data Index: 585981 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6998. Min Range: -4.6998
Max Act: 4.3561. Min Act: -0.1700
Data Index: 596202 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6998. Min Range: -4.6998
Max Act: 4.3561. Min Act: -0.1700
Data Index: 910808 (C4 (Web Text))
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6998. Min Range: -4.6998
Max Act: 4.3873. Min Act: -0.1700
Data Index: 872350 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6998. Min Range: -4.6998
Max Act: 4.3873. Min Act: -0.1700
Data Index: 997855 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6998. Min Range: -4.6998
Max Act: 4.2935. Min Act: -0.1700
Data Index: 678826 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6998. Min Range: -4.6998
Max Act: 4.3248. Min Act: -0.1700
Data Index: 302195 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6998. Min Range: -4.6998
Max Act: 4.3561. Min Act: -0.1700
Data Index: 250913 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6998. Min Range: -4.6998
Max Act: 4.3561. Min Act: -0.1700
Data Index: 548893 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19