Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 2518 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 1.2411. Min Range: -1.2411
Max Act: 1.2411. Min Act: -0.0001
Data Index: 1244074 (The Pile)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2411. Min Range: -1.2411
Max Act: 1.1464. Min Act: -0.0001
Data Index: 1614556 (The Pile)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2411. Min Range: -1.2411
Max Act: 1.0720. Min Act: -0.0001
Data Index: 1741138 (The Pile)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2411. Min Range: -1.2411
Max Act: 1.0874. Min Act: -0.0001
Data Index: 207410 (The Pile)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2411. Min Range: -1.2411
Max Act: 1.0487. Min Act: -0.0001
Data Index: 226730 (The Pile)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2411. Min Range: -1.2411
Max Act: 1.0488. Min Act: -0.0001
Data Index: 59227 (The Pile)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2411. Min Range: -1.2411
Max Act: 1.0600. Min Act: -0.0001
Data Index: 556768 (The Pile)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2411. Min Range: -1.2411
Max Act: 1.0375. Min Act: -0.0001
Data Index: 1888811 (The Pile)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2411. Min Range: -1.2411
Max Act: 0.9005. Min Act: -0.0001
Data Index: 1023420 (The Pile)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2411. Min Range: -1.2411
Max Act: 0.8979. Min Act: -0.0001
Data Index: 1082511 (The Pile)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2411. Min Range: -1.2411
Max Act: 0.9554. Min Act: -0.0001
Data Index: 236684 (The Pile)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2411. Min Range: -1.2411
Max Act: 0.9657. Min Act: -0.0001
Data Index: 848740 (The Pile)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2411. Min Range: -1.2411
Max Act: 0.9355. Min Act: -0.0001
Data Index: 896494 (The Pile)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2411. Min Range: -1.2411
Max Act: 0.9057. Min Act: -0.0001
Data Index: 866818 (The Pile)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2411. Min Range: -1.2411
Max Act: 0.9011. Min Act: -0.0001
Data Index: 1982137 (The Pile)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2411. Min Range: -1.2411
Max Act: 0.9600. Min Act: -0.0001
Data Index: 489353 (The Pile)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2411. Min Range: -1.2411
Max Act: 0.8783. Min Act: -0.0001
Data Index: 1818835 (The Pile)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2411. Min Range: -1.2411
Max Act: 0.9508. Min Act: -0.0001
Data Index: 1296868 (The Pile)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2411. Min Range: -1.2411
Max Act: 0.9243. Min Act: -0.0001
Data Index: 1136851 (The Pile)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2411. Min Range: -1.2411
Max Act: 0.9530. Min Act: -0.0001
Data Index: 957583 (The Pile)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19