Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1267 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.7404. Min Range: -1.7404
Max Act: 1.7404. Min Act: -0.0000
Data Index: 1575935 (The Pile)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7404. Min Range: -1.7404
Max Act: 1.5251. Min Act: -0.0000
Data Index: 345330 (The Pile)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7404. Min Range: -1.7404
Max Act: 1.3055. Min Act: -0.0000
Data Index: 262126 (The Pile)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7404. Min Range: -1.7404
Max Act: 1.3192. Min Act: 0.0001
Data Index: 862118 (The Pile)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7404. Min Range: -1.7404
Max Act: 1.3297. Min Act: -0.0000
Data Index: 742074 (The Pile)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7404. Min Range: -1.7404
Max Act: 1.3511. Min Act: 0.0000
Data Index: 1285970 (The Pile)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7404. Min Range: -1.7404
Max Act: 1.2549. Min Act: 0.0000
Data Index: 1493141 (The Pile)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7404. Min Range: -1.7404
Max Act: 1.1520. Min Act: 0.0000
Data Index: 1839578 (The Pile)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7404. Min Range: -1.7404
Max Act: 1.2283. Min Act: -0.0000
Data Index: 952004 (The Pile)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7404. Min Range: -1.7404
Max Act: 1.1792. Min Act: 0.0000
Data Index: 324942 (The Pile)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7404. Min Range: -1.7404
Max Act: 1.2589. Min Act: -0.0000
Data Index: 998488 (The Pile)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7404. Min Range: -1.7404
Max Act: 1.1426. Min Act: 0.0001
Data Index: 1057932 (The Pile)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7404. Min Range: -1.7404
Max Act: 1.4028. Min Act: -0.0000
Data Index: 228765 (The Pile)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7404. Min Range: -1.7404
Max Act: 1.1160. Min Act: 0.0000
Data Index: 1231255 (The Pile)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7404. Min Range: -1.7404
Max Act: 1.0936. Min Act: -0.0000
Data Index: 995282 (The Pile)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7404. Min Range: -1.7404
Max Act: 1.0886. Min Act: 0.0000
Data Index: 1578542 (The Pile)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7404. Min Range: -1.7404
Max Act: 1.0464. Min Act: 0.0000
Data Index: 809700 (The Pile)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7404. Min Range: -1.7404
Max Act: 1.0108. Min Act: -0.0000
Data Index: 928563 (The Pile)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7404. Min Range: -1.7404
Max Act: 1.0356. Min Act: -0.0000
Data Index: 83220 (The Pile)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7404. Min Range: -1.7404
Max Act: 1.0279. Min Act: 0.0000
Data Index: 722428 (The Pile)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19