Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1006 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.1003. Min Range: -4.1003
Max Act: 4.1003. Min Act: -0.1700
Data Index: 550761 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1003. Min Range: -4.1003
Max Act: 4.0378. Min Act: -0.1700
Data Index: 991239 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1003. Min Range: -4.1003
Max Act: 4.0691. Min Act: -0.1700
Data Index: 63883 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1003. Min Range: -4.1003
Max Act: 4.0065. Min Act: -0.1700
Data Index: 39398 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1003. Min Range: -4.1003
Max Act: 4.0378. Min Act: -0.1700
Data Index: 751500 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1003. Min Range: -4.1003
Max Act: 4.0065. Min Act: -0.1699
Data Index: 1086387 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1003. Min Range: -4.1003
Max Act: 3.9753. Min Act: -0.1700
Data Index: 90433 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1003. Min Range: -4.1003
Max Act: 4.0065. Min Act: -0.1700
Data Index: 967299 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1003. Min Range: -4.1003
Max Act: 3.9753. Min Act: -0.1700
Data Index: 1220602 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1003. Min Range: -4.1003
Max Act: 3.9753. Min Act: -0.1700
Data Index: 851385 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1003. Min Range: -4.1003
Max Act: 3.9753. Min Act: -0.1700
Data Index: 772282 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1003. Min Range: -4.1003
Max Act: 3.9440. Min Act: -0.1700
Data Index: 1388684 (Python Code)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1003. Min Range: -4.1003
Max Act: 3.9440. Min Act: -0.1700
Data Index: 113912 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1003. Min Range: -4.1003
Max Act: 3.9440. Min Act: -0.1700
Data Index: 441619 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1003. Min Range: -4.1003
Max Act: 3.9753. Min Act: -0.1700
Data Index: 73641 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1003. Min Range: -4.1003
Max Act: 3.9753. Min Act: -0.1700
Data Index: 311729 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1003. Min Range: -4.1003
Max Act: 3.9440. Min Act: -0.1700
Data Index: 661633 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1003. Min Range: -4.1003
Max Act: 3.9440. Min Act: -0.1700
Data Index: 668687 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1003. Min Range: -4.1003
Max Act: 3.9127. Min Act: -0.1700
Data Index: 818731 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1003. Min Range: -4.1003
Max Act: 3.9127. Min Act: -0.1700
Data Index: 250522 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #19