Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 253 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 2.1685. Min Range: -2.1685
Max Act: 2.1211. Min Act: -0.0000
Data Index: 1284995 (The Pile)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1685. Min Range: -2.1685
Max Act: 2.0089. Min Act: -0.0001
Data Index: 1162972 (The Pile)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1685. Min Range: -2.1685
Max Act: 1.8463. Min Act: -0.0000
Data Index: 222438 (The Pile)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1685. Min Range: -2.1685
Max Act: 2.1597. Min Act: -0.0000
Data Index: 1838886 (The Pile)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1685. Min Range: -2.1685
Max Act: 2.0311. Min Act: -0.0000
Data Index: 483235 (The Pile)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1685. Min Range: -2.1685
Max Act: 1.9558. Min Act: -0.0001
Data Index: 1905624 (The Pile)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1685. Min Range: -2.1685
Max Act: 2.1685. Min Act: -0.0001
Data Index: 1721335 (The Pile)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1685. Min Range: -2.1685
Max Act: 1.9782. Min Act: -0.0001
Data Index: 665628 (The Pile)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1685. Min Range: -2.1685
Max Act: 2.0520. Min Act: -0.0000
Data Index: 1253382 (The Pile)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1685. Min Range: -2.1685
Max Act: 2.0520. Min Act: -0.0000
Data Index: 1790450 (The Pile)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1685. Min Range: -2.1685
Max Act: 2.0403. Min Act: -0.0000
Data Index: 77808 (The Pile)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1685. Min Range: -2.1685
Max Act: 2.0403. Min Act: -0.0001
Data Index: 1548693 (The Pile)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1685. Min Range: -2.1685
Max Act: 2.0683. Min Act: -0.0001
Data Index: 1449693 (The Pile)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1685. Min Range: -2.1685
Max Act: 1.6019. Min Act: -0.0000
Data Index: 1271765 (The Pile)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1685. Min Range: -2.1685
Max Act: 2.1024. Min Act: -0.0001
Data Index: 1931412 (The Pile)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1685. Min Range: -2.1685
Max Act: 1.9891. Min Act: -0.0001
Data Index: 1438348 (The Pile)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1685. Min Range: -2.1685
Max Act: 2.0977. Min Act: -0.0000
Data Index: 1114121 (The Pile)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1685. Min Range: -2.1685
Max Act: 1.9633. Min Act: -0.0001
Data Index: 869268 (The Pile)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1685. Min Range: -2.1685
Max Act: 1.8677. Min Act: -0.0000
Data Index: 1005139 (The Pile)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1685. Min Range: -2.1685
Max Act: 1.9585. Min Act: -0.0001
Data Index: 1080071 (The Pile)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #19