Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 1194 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 3.8091. Min Range: -3.8091
Max Act: 3.8091. Min Act: -0.0001
Data Index: 1104819 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8091. Min Range: -3.8091
Max Act: 3.8091. Min Act: -0.0001
Data Index: 1183693 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8091. Min Range: -3.8091
Max Act: 3.8091. Min Act: -0.0001
Data Index: 1845920 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8091. Min Range: -3.8091
Max Act: 3.0753. Min Act: -0.0001
Data Index: 1428363 (The Pile)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8091. Min Range: -3.8091
Max Act: 2.9333. Min Act: -0.0001
Data Index: 743656 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8091. Min Range: -3.8091
Max Act: 2.9333. Min Act: -0.0001
Data Index: 1551853 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8091. Min Range: -3.8091
Max Act: 3.0676. Min Act: -0.0001
Data Index: 1459176 (The Pile)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8091. Min Range: -3.8091
Max Act: 2.8321. Min Act: -0.0001
Data Index: 1456235 (The Pile)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8091. Min Range: -3.8091
Max Act: 2.9519. Min Act: -0.0001
Data Index: 510203 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8091. Min Range: -3.8091
Max Act: 2.7474. Min Act: -0.0001
Data Index: 931117 (The Pile)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8091. Min Range: -3.8091
Max Act: 2.8630. Min Act: -0.0001
Data Index: 610748 (The Pile)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8091. Min Range: -3.8091
Max Act: 2.6973. Min Act: -0.0001
Data Index: 1347238 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8091. Min Range: -3.8091
Max Act: 2.5812. Min Act: -0.0001
Data Index: 1385409 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8091. Min Range: -3.8091
Max Act: 2.5478. Min Act: -0.0001
Data Index: 1432959 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8091. Min Range: -3.8091
Max Act: 2.3937. Min Act: -0.0001
Data Index: 565989 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8091. Min Range: -3.8091
Max Act: 2.5324. Min Act: -0.0001
Data Index: 967975 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8091. Min Range: -3.8091
Max Act: 2.3979. Min Act: -0.0001
Data Index: 1333217 (The Pile)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8091. Min Range: -3.8091
Max Act: 2.4965. Min Act: -0.0001
Data Index: 35698 (The Pile)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8091. Min Range: -3.8091
Max Act: 2.4620. Min Act: -0.0001
Data Index: 1480255 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8091. Min Range: -3.8091
Max Act: 2.3674. Min Act: -0.0001
Data Index: 857596 (The Pile)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19