Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 901 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.4378. Min Act: -0.0001
Data Index: 1506803 (The Pile)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3955. Min Act: -0.0001
Data Index: 1517015 (The Pile)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.4016. Min Act: -0.0001
Data Index: 1478674 (The Pile)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3988. Min Act: -0.0001
Data Index: 1827607 (The Pile)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3778. Min Act: -0.0001
Data Index: 1363388 (The Pile)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3806. Min Act: -0.0001
Data Index: 1071949 (The Pile)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3809. Min Act: -0.0001
Data Index: 1952616 (The Pile)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.4046. Min Act: -0.0001
Data Index: 21394 (The Pile)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3788. Min Act: -0.0001
Data Index: 1971742 (The Pile)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3770. Min Act: -0.0001
Data Index: 207970 (The Pile)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3867. Min Act: -0.0001
Data Index: 36903 (The Pile)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3880. Min Act: -0.0001
Data Index: 1963968 (The Pile)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.4057. Min Act: -0.0001
Data Index: 1672076 (The Pile)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3965. Min Act: -0.0001
Data Index: 1894967 (The Pile)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3543. Min Act: -0.0001
Data Index: 1579688 (The Pile)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3789. Min Act: -0.0001
Data Index: 1034746 (The Pile)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3453. Min Act: -0.0001
Data Index: 1624308 (The Pile)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3957. Min Act: -0.0001
Data Index: 97138 (The Pile)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3808. Min Act: -0.0001
Data Index: 693468 (The Pile)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4378. Min Range: -0.4378
Max Act: 0.3725. Min Act: -0.0001
Data Index: 590188 (The Pile)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19