Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1255 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.9335. Min Range: -2.9335
Max Act: 2.9335. Min Act: -0.0000
Data Index: 302460 (The Pile)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9335. Min Range: -2.9335
Max Act: 2.7157. Min Act: -0.0000
Data Index: 541710 (The Pile)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9335. Min Range: -2.9335
Max Act: 2.7654. Min Act: -0.0000
Data Index: 1819299 (The Pile)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9335. Min Range: -2.9335
Max Act: 2.8799. Min Act: -0.0000
Data Index: 848414 (The Pile)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9335. Min Range: -2.9335
Max Act: 2.6399. Min Act: -0.0000
Data Index: 448296 (The Pile)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9335. Min Range: -2.9335
Max Act: 2.3999. Min Act: -0.0000
Data Index: 1289753 (The Pile)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9335. Min Range: -2.9335
Max Act: 2.5529. Min Act: -0.0000
Data Index: 898016 (The Pile)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9335. Min Range: -2.9335
Max Act: 2.5841. Min Act: -0.0000
Data Index: 1808745 (The Pile)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9335. Min Range: -2.9335
Max Act: 2.3509. Min Act: -0.0000
Data Index: 424500 (The Pile)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9335. Min Range: -2.9335
Max Act: 2.3131. Min Act: -0.0000
Data Index: 891358 (The Pile)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9335. Min Range: -2.9335
Max Act: 2.4194. Min Act: -0.0000
Data Index: 241999 (The Pile)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9335. Min Range: -2.9335
Max Act: 2.3948. Min Act: -0.0000
Data Index: 1298357 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9335. Min Range: -2.9335
Max Act: 2.2252. Min Act: -0.0000
Data Index: 891338 (The Pile)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9335. Min Range: -2.9335
Max Act: 2.2180. Min Act: -0.0000
Data Index: 1425144 (The Pile)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9335. Min Range: -2.9335
Max Act: 2.2090. Min Act: -0.0000
Data Index: 994329 (The Pile)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9335. Min Range: -2.9335
Max Act: 2.1998. Min Act: -0.0000
Data Index: 208024 (The Pile)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9335. Min Range: -2.9335
Max Act: 2.1743. Min Act: -0.0000
Data Index: 68159 (The Pile)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9335. Min Range: -2.9335
Max Act: 2.1407. Min Act: -0.0000
Data Index: 1823855 (The Pile)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9335. Min Range: -2.9335
Max Act: 2.0233. Min Act: -0.0000
Data Index: 1287646 (The Pile)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9335. Min Range: -2.9335
Max Act: 2.1269. Min Act: -0.0000
Data Index: 1502503 (The Pile)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19