Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 750 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.3578. Min Range: -2.3578
Max Act: 2.3578. Min Act: -0.0000
Data Index: 1882942 (The Pile)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3578. Min Range: -2.3578
Max Act: 2.3407. Min Act: -0.0000
Data Index: 615091 (The Pile)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3578. Min Range: -2.3578
Max Act: 2.2177. Min Act: -0.0000
Data Index: 1921163 (The Pile)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3578. Min Range: -2.3578
Max Act: 2.1803. Min Act: -0.0000
Data Index: 66541 (The Pile)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3578. Min Range: -2.3578
Max Act: 2.1282. Min Act: -0.0000
Data Index: 952702 (The Pile)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3578. Min Range: -2.3578
Max Act: 2.0750. Min Act: -0.0000
Data Index: 408729 (The Pile)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3578. Min Range: -2.3578
Max Act: 2.0295. Min Act: -0.0000
Data Index: 724796 (The Pile)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3578. Min Range: -2.3578
Max Act: 2.0156. Min Act: -0.0000
Data Index: 1483932 (The Pile)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3578. Min Range: -2.3578
Max Act: 2.0776. Min Act: -0.0000
Data Index: 1426190 (The Pile)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3578. Min Range: -2.3578
Max Act: 2.1085. Min Act: -0.0000
Data Index: 1785897 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3578. Min Range: -2.3578
Max Act: 2.1085. Min Act: -0.0000
Data Index: 1799617 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3578. Min Range: -2.3578
Max Act: 1.9175. Min Act: -0.0000
Data Index: 436357 (The Pile)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3578. Min Range: -2.3578
Max Act: 1.9860. Min Act: -0.0000
Data Index: 1920789 (The Pile)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3578. Min Range: -2.3578
Max Act: 1.9778. Min Act: -0.0000
Data Index: 812279 (The Pile)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3578. Min Range: -2.3578
Max Act: 1.9175. Min Act: -0.0000
Data Index: 1518540 (The Pile)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3578. Min Range: -2.3578
Max Act: 1.8851. Min Act: -0.0000
Data Index: 1655957 (The Pile)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3578. Min Range: -2.3578
Max Act: 1.8541. Min Act: -0.0000
Data Index: 105249 (The Pile)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3578. Min Range: -2.3578
Max Act: 1.9759. Min Act: -0.0000
Data Index: 1122110 (The Pile)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3578. Min Range: -2.3578
Max Act: 1.9509. Min Act: -0.0000
Data Index: 1490735 (The Pile)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3578. Min Range: -2.3578
Max Act: 1.8416. Min Act: -0.0000
Data Index: 1534182 (The Pile)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19