Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 3637 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.7279. Min Range: -1.7279
Max Act: 1.7279. Min Act: -0.0001
Data Index: 185652 (The Pile)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7279. Min Range: -1.7279
Max Act: 1.5324. Min Act: -0.0001
Data Index: 38986 (The Pile)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7279. Min Range: -1.7279
Max Act: 1.2643. Min Act: -0.0001
Data Index: 558656 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7279. Min Range: -1.7279
Max Act: 1.4396. Min Act: -0.0001
Data Index: 549927 (The Pile)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7279. Min Range: -1.7279
Max Act: 1.4650. Min Act: -0.0001
Data Index: 1075137 (The Pile)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7279. Min Range: -1.7279
Max Act: 1.1972. Min Act: -0.0001
Data Index: 840276 (The Pile)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7279. Min Range: -1.7279
Max Act: 1.3295. Min Act: -0.0001
Data Index: 1794344 (The Pile)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7279. Min Range: -1.7279
Max Act: 1.2868. Min Act: -0.0001
Data Index: 90948 (The Pile)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7279. Min Range: -1.7279
Max Act: 1.4464. Min Act: -0.0001
Data Index: 851171 (The Pile)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7279. Min Range: -1.7279
Max Act: 1.2411. Min Act: -0.0001
Data Index: 857060 (The Pile)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7279. Min Range: -1.7279
Max Act: 1.1895. Min Act: -0.0001
Data Index: 369895 (The Pile)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7279. Min Range: -1.7279
Max Act: 1.2520. Min Act: -0.0001
Data Index: 556717 (The Pile)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7279. Min Range: -1.7279
Max Act: 1.1235. Min Act: -0.0001
Data Index: 1823687 (The Pile)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7279. Min Range: -1.7279
Max Act: 1.1432. Min Act: -0.0001
Data Index: 1304824 (The Pile)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7279. Min Range: -1.7279
Max Act: 1.1728. Min Act: -0.0001
Data Index: 1890564 (The Pile)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7279. Min Range: -1.7279
Max Act: 1.1314. Min Act: -0.0001
Data Index: 771309 (The Pile)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7279. Min Range: -1.7279
Max Act: 1.1521. Min Act: -0.0001
Data Index: 1000884 (The Pile)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7279. Min Range: -1.7279
Max Act: 1.1798. Min Act: -0.0001
Data Index: 643025 (The Pile)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7279. Min Range: -1.7279
Max Act: 1.1361. Min Act: -0.0001
Data Index: 1483321 (The Pile)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7279. Min Range: -1.7279
Max Act: 1.1419. Min Act: -0.0001
Data Index: 1275963 (The Pile)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19