Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 918 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.7219. Min Range: -1.7219
Max Act: 1.5764. Min Act: -0.0000
Data Index: 443771 (The Pile)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7219. Min Range: -1.7219
Max Act: 1.7219. Min Act: -0.0000
Data Index: 1393502 (The Pile)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7219. Min Range: -1.7219
Max Act: 1.3367. Min Act: -0.0000
Data Index: 1132138 (The Pile)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7219. Min Range: -1.7219
Max Act: 1.6537. Min Act: -0.0000
Data Index: 1319234 (The Pile)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7219. Min Range: -1.7219
Max Act: 1.6049. Min Act: -0.0000
Data Index: 1983506 (The Pile)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7219. Min Range: -1.7219
Max Act: 1.3362. Min Act: -0.0000
Data Index: 1846768 (The Pile)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7219. Min Range: -1.7219
Max Act: 1.3910. Min Act: -0.0001
Data Index: 32818 (The Pile)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7219. Min Range: -1.7219
Max Act: 1.5138. Min Act: -0.0000
Data Index: 1076926 (The Pile)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7219. Min Range: -1.7219
Max Act: 1.4739. Min Act: -0.0000
Data Index: 737120 (The Pile)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7219. Min Range: -1.7219
Max Act: 1.4334. Min Act: -0.0000
Data Index: 903787 (The Pile)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7219. Min Range: -1.7219
Max Act: 1.4213. Min Act: -0.0000
Data Index: 1461873 (The Pile)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7219. Min Range: -1.7219
Max Act: 1.5468. Min Act: -0.0000
Data Index: 279578 (The Pile)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7219. Min Range: -1.7219
Max Act: 1.4137. Min Act: -0.0000
Data Index: 223287 (The Pile)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7219. Min Range: -1.7219
Max Act: 1.4370. Min Act: -0.0000
Data Index: 953987 (The Pile)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7219. Min Range: -1.7219
Max Act: 1.2245. Min Act: -0.0000
Data Index: 1501452 (The Pile)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7219. Min Range: -1.7219
Max Act: 1.4142. Min Act: -0.0000
Data Index: 260148 (The Pile)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7219. Min Range: -1.7219
Max Act: 1.4081. Min Act: -0.0000
Data Index: 770649 (The Pile)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7219. Min Range: -1.7219
Max Act: 1.2750. Min Act: -0.0000
Data Index: 225342 (The Pile)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7219. Min Range: -1.7219
Max Act: 1.1324. Min Act: -0.0000
Data Index: 1576998 (The Pile)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7219. Min Range: -1.7219
Max Act: 1.2032. Min Act: -0.0000
Data Index: 258238 (The Pile)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19