Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1132 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.4619. Min Range: -0.4619
Max Act: 0.4619. Min Act: -0.0001
Data Index: 264137 (The Pile)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4619. Min Range: -0.4619
Max Act: 0.4098. Min Act: -0.0001
Data Index: 334043 (The Pile)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4619. Min Range: -0.4619
Max Act: 0.4565. Min Act: -0.0001
Data Index: 665030 (The Pile)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4619. Min Range: -0.4619
Max Act: 0.4236. Min Act: -0.0001
Data Index: 1710718 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4619. Min Range: -0.4619
Max Act: 0.4236. Min Act: -0.0001
Data Index: 8947 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4619. Min Range: -0.4619
Max Act: 0.4005. Min Act: -0.0001
Data Index: 754879 (The Pile)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4619. Min Range: -0.4619
Max Act: 0.3977. Min Act: -0.0001
Data Index: 1011704 (The Pile)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4619. Min Range: -0.4619
Max Act: 0.4306. Min Act: -0.0001
Data Index: 1950854 (The Pile)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4619. Min Range: -0.4619
Max Act: 0.4165. Min Act: -0.0001
Data Index: 1099172 (The Pile)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4619. Min Range: -0.4619
Max Act: 0.4243. Min Act: -0.0001
Data Index: 1083830 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4619. Min Range: -0.4619
Max Act: 0.3827. Min Act: -0.0001
Data Index: 1490060 (The Pile)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4619. Min Range: -0.4619
Max Act: 0.3955. Min Act: -0.0001
Data Index: 1300540 (The Pile)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4619. Min Range: -0.4619
Max Act: 0.4017. Min Act: -0.0001
Data Index: 1327693 (The Pile)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4619. Min Range: -0.4619
Max Act: 0.4100. Min Act: -0.0001
Data Index: 665455 (The Pile)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4619. Min Range: -0.4619
Max Act: 0.3674. Min Act: -0.0001
Data Index: 1196960 (The Pile)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4619. Min Range: -0.4619
Max Act: 0.3934. Min Act: -0.0001
Data Index: 1435807 (The Pile)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4619. Min Range: -0.4619
Max Act: 0.3956. Min Act: -0.0001
Data Index: 1543669 (The Pile)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4619. Min Range: -0.4619
Max Act: 0.4074. Min Act: -0.0001
Data Index: 477517 (The Pile)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4619. Min Range: -0.4619
Max Act: 0.3923. Min Act: -0.0001
Data Index: 1397377 (The Pile)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4619. Min Range: -0.4619
Max Act: 0.3685. Min Act: -0.0001
Data Index: 1888769 (The Pile)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19