Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1216 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.1244. Min Range: -1.1244
Max Act: 1.1244. Min Act: -0.0001
Data Index: 1065039 (The Pile)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1244. Min Range: -1.1244
Max Act: 1.0836. Min Act: -0.0001
Data Index: 102335 (The Pile)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1244. Min Range: -1.1244
Max Act: 1.1104. Min Act: -0.0001
Data Index: 1280950 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1244. Min Range: -1.1244
Max Act: 1.0250. Min Act: -0.0001
Data Index: 611737 (The Pile)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1244. Min Range: -1.1244
Max Act: 1.1032. Min Act: -0.0001
Data Index: 1879588 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1244. Min Range: -1.1244
Max Act: 1.0228. Min Act: -0.0001
Data Index: 797638 (The Pile)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1244. Min Range: -1.1244
Max Act: 1.0139. Min Act: -0.0001
Data Index: 946058 (The Pile)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1244. Min Range: -1.1244
Max Act: 1.0625. Min Act: -0.0001
Data Index: 1621119 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1244. Min Range: -1.1244
Max Act: 0.9272. Min Act: -0.0001
Data Index: 630646 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1244. Min Range: -1.1244
Max Act: 0.9993. Min Act: -0.0001
Data Index: 211419 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1244. Min Range: -1.1244
Max Act: 0.9631. Min Act: -0.0001
Data Index: 12268 (The Pile)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1244. Min Range: -1.1244
Max Act: 0.9966. Min Act: -0.0001
Data Index: 1088708 (The Pile)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1244. Min Range: -1.1244
Max Act: 0.9707. Min Act: -0.0001
Data Index: 236144 (The Pile)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1244. Min Range: -1.1244
Max Act: 0.9911. Min Act: -0.0001
Data Index: 772996 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1244. Min Range: -1.1244
Max Act: 1.0210. Min Act: -0.0001
Data Index: 64369 (The Pile)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1244. Min Range: -1.1244
Max Act: 0.9907. Min Act: -0.0001
Data Index: 1381530 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1244. Min Range: -1.1244
Max Act: 1.0287. Min Act: -0.0001
Data Index: 547658 (The Pile)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1244. Min Range: -1.1244
Max Act: 0.9759. Min Act: -0.0001
Data Index: 1465088 (The Pile)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1244. Min Range: -1.1244
Max Act: 0.9825. Min Act: -0.0001
Data Index: 155882 (The Pile)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1244. Min Range: -1.1244
Max Act: 0.9485. Min Act: -0.0001
Data Index: 617849 (The Pile)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19