Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1639 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.1103. Min Range: -0.1103
Max Act: 0.1103. Min Act: -0.0001
Data Index: 137773 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1103. Min Range: -0.1103
Max Act: 0.1028. Min Act: -0.0001
Data Index: 503141 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1103. Min Range: -0.1103
Max Act: 0.1034. Min Act: -0.0001
Data Index: 1178060 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1103. Min Range: -0.1103
Max Act: 0.1030. Min Act: -0.0001
Data Index: 1163547 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1103. Min Range: -0.1103
Max Act: 0.0931. Min Act: -0.0001
Data Index: 599632 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1103. Min Range: -0.1103
Max Act: 0.0899. Min Act: -0.0001
Data Index: 964406 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1103. Min Range: -0.1103
Max Act: 0.0902. Min Act: -0.0002
Data Index: 969406 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1103. Min Range: -0.1103
Max Act: 0.1006. Min Act: -0.0001
Data Index: 395533 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1103. Min Range: -0.1103
Max Act: 0.0965. Min Act: -0.0001
Data Index: 91463 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1103. Min Range: -0.1103
Max Act: 0.0951. Min Act: -0.0001
Data Index: 370904 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1103. Min Range: -0.1103
Max Act: 0.0905. Min Act: -0.0001
Data Index: 665015 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1103. Min Range: -0.1103
Max Act: 0.0950. Min Act: -0.0001
Data Index: 474651 (C4 (Web Text))
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1103. Min Range: -0.1103
Max Act: 0.0879. Min Act: -0.0001
Data Index: 195419 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1103. Min Range: -0.1103
Max Act: 0.0936. Min Act: -0.0001
Data Index: 1178038 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1103. Min Range: -0.1103
Max Act: 0.0935. Min Act: -0.0001
Data Index: 1084399 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1103. Min Range: -0.1103
Max Act: 0.0962. Min Act: -0.0001
Data Index: 925068 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1103. Min Range: -0.1103
Max Act: 0.0927. Min Act: -0.0001
Data Index: 1092173 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1103. Min Range: -0.1103
Max Act: 0.0918. Min Act: -0.0001
Data Index: 305913 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1103. Min Range: -0.1103
Max Act: 0.0918. Min Act: -0.0001
Data Index: 174074 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1103. Min Range: -0.1103
Max Act: 0.0926. Min Act: -0.0001
Data Index: 300270 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19