Model: SoLU Model: 4 Layers, 2048 Neurons per Layer
Dataset: The Pile
Neuron 1165 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')
Text #0
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.4416. Min Act: 0.0001
Data Index: 503335 (The Pile)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.4007. Min Act: -0.0001
Data Index: 706940 (The Pile)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3715. Min Act: -0.0001
Data Index: 1537085 (The Pile)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3668. Min Act: -0.0000
Data Index: 954920 (The Pile)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3784. Min Act: -0.0000
Data Index: 1570538 (The Pile)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3779. Min Act: -0.0001
Data Index: 963811 (The Pile)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3764. Min Act: -0.0001
Data Index: 596560 (The Pile)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3772. Min Act: -0.0000
Data Index: 540647 (The Pile)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3711. Min Act: 0.0000
Data Index: 630 (The Pile)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3740. Min Act: 0.0000
Data Index: 1940431 (The Pile)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3818. Min Act: 0.0000
Data Index: 1557761 (The Pile)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3696. Min Act: -0.0001
Data Index: 1021511 (The Pile)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3677. Min Act: -0.0001
Data Index: 1606705 (The Pile)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3645. Min Act: -0.0001
Data Index: 297949 (The Pile)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3524. Min Act: -0.0001
Data Index: 297687 (The Pile)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3656. Min Act: -0.0000
Data Index: 1832201 (The Pile)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3601. Min Act: -0.0000
Data Index: 1523047 (The Pile)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3507. Min Act: 0.0000
Data Index: 1021037 (The Pile)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3617. Min Act: -0.0001
Data Index: 1729866 (The Pile)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3600. Min Act: -0.0001
Data Index: 1127762 (The Pile)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19