Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2846 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.5081. Min Range: -2.5081
Max Act: 2.3072. Min Act: -0.0001
Data Index: 1315341 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5081. Min Range: -2.5081
Max Act: 2.2988. Min Act: -0.0000
Data Index: 382616 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5081. Min Range: -2.5081
Max Act: 2.2868. Min Act: -0.0001
Data Index: 1010353 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5081. Min Range: -2.5081
Max Act: 2.5081. Min Act: -0.0001
Data Index: 1201908 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5081. Min Range: -2.5081
Max Act: 2.2541. Min Act: -0.0001
Data Index: 48671 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5081. Min Range: -2.5081
Max Act: 2.3748. Min Act: -0.0001
Data Index: 1111093 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5081. Min Range: -2.5081
Max Act: 2.2829. Min Act: -0.0001
Data Index: 547201 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5081. Min Range: -2.5081
Max Act: 2.1458. Min Act: -0.0001
Data Index: 225559 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5081. Min Range: -2.5081
Max Act: 2.2054. Min Act: -0.0001
Data Index: 721168 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5081. Min Range: -2.5081
Max Act: 1.9985. Min Act: -0.0001
Data Index: 452558 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5081. Min Range: -2.5081
Max Act: 2.3041. Min Act: -0.0001
Data Index: 1176504 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5081. Min Range: -2.5081
Max Act: 2.1595. Min Act: -0.0000
Data Index: 252798 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5081. Min Range: -2.5081
Max Act: 2.0952. Min Act: -0.0001
Data Index: 443786 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5081. Min Range: -2.5081
Max Act: 2.3243. Min Act: -0.0001
Data Index: 37881 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5081. Min Range: -2.5081
Max Act: 2.0819. Min Act: -0.0001
Data Index: 1175832 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5081. Min Range: -2.5081
Max Act: 2.0986. Min Act: -0.0000
Data Index: 1042944 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5081. Min Range: -2.5081
Max Act: 1.9517. Min Act: -0.0001
Data Index: 873001 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5081. Min Range: -2.5081
Max Act: 1.9413. Min Act: -0.0001
Data Index: 271753 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5081. Min Range: -2.5081
Max Act: 1.7391. Min Act: -0.0001
Data Index: 1063039 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5081. Min Range: -2.5081
Max Act: 2.0139. Min Act: -0.0001
Data Index: 291669 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19