Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 3486 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.0287. Min Range: -0.0287
Max Act: 0.0287. Min Act: -0.0002
Data Index: 1054781 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0287. Min Range: -0.0287
Max Act: 0.0233. Min Act: -0.0002
Data Index: 1122825 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0287. Min Range: -0.0287
Max Act: 0.0234. Min Act: -0.0002
Data Index: 1724295 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0287. Min Range: -0.0287
Max Act: 0.0244. Min Act: -0.0002
Data Index: 356910 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0287. Min Range: -0.0287
Max Act: 0.0225. Min Act: -0.0002
Data Index: 770700 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0287. Min Range: -0.0287
Max Act: 0.0236. Min Act: -0.0002
Data Index: 906031 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0287. Min Range: -0.0287
Max Act: 0.0225. Min Act: -0.0002
Data Index: 399374 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0287. Min Range: -0.0287
Max Act: 0.0228. Min Act: -0.0002
Data Index: 1719295 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0287. Min Range: -0.0287
Max Act: 0.0225. Min Act: -0.0002
Data Index: 817391 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0287. Min Range: -0.0287
Max Act: 0.0225. Min Act: -0.0002
Data Index: 388953 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0287. Min Range: -0.0287
Max Act: 0.0216. Min Act: -0.0002
Data Index: 1959446 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0287. Min Range: -0.0287
Max Act: 0.0229. Min Act: -0.0002
Data Index: 1268980 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0287. Min Range: -0.0287
Max Act: 0.0212. Min Act: -0.0002
Data Index: 1024162 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0287. Min Range: -0.0287
Max Act: 0.0211. Min Act: -0.0002
Data Index: 737274 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0287. Min Range: -0.0287
Max Act: 0.0217. Min Act: -0.0002
Data Index: 464458 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0287. Min Range: -0.0287
Max Act: 0.0220. Min Act: -0.0002
Data Index: 1616989 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0287. Min Range: -0.0287
Max Act: 0.0211. Min Act: -0.0002
Data Index: 229316 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0287. Min Range: -0.0287
Max Act: 0.0202. Min Act: -0.0002
Data Index: 966661 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0287. Min Range: -0.0287
Max Act: 0.0216. Min Act: -0.0002
Data Index: 1744421 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0287. Min Range: -0.0287
Max Act: 0.0203. Min Act: -0.0002
Data Index: 1995086 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19