Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 3658 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.5929. Min Range: -2.5929
Max Act: 2.5929. Min Act: -0.0001
Data Index: 1222928 (The Pile)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5929. Min Range: -2.5929
Max Act: 1.5683. Min Act: -0.0001
Data Index: 782722 (The Pile)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5929. Min Range: -2.5929
Max Act: 1.5665. Min Act: -0.0001
Data Index: 981930 (The Pile)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5929. Min Range: -2.5929
Max Act: 1.7194. Min Act: -0.0001
Data Index: 1160492 (The Pile)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5929. Min Range: -2.5929
Max Act: 1.5738. Min Act: -0.0001
Data Index: 911575 (The Pile)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5929. Min Range: -2.5929
Max Act: 1.5011. Min Act: -0.0001
Data Index: 1416385 (The Pile)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5929. Min Range: -2.5929
Max Act: 1.5452. Min Act: -0.0001
Data Index: 31436 (The Pile)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5929. Min Range: -2.5929
Max Act: 1.5062. Min Act: -0.0001
Data Index: 1964940 (The Pile)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5929. Min Range: -2.5929
Max Act: 1.4968. Min Act: -0.0001
Data Index: 527701 (The Pile)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5929. Min Range: -2.5929
Max Act: 1.4867. Min Act: -0.0001
Data Index: 1324698 (The Pile)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5929. Min Range: -2.5929
Max Act: 1.2656. Min Act: -0.0001
Data Index: 775760 (The Pile)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5929. Min Range: -2.5929
Max Act: 1.3858. Min Act: -0.0001
Data Index: 1241855 (The Pile)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5929. Min Range: -2.5929
Max Act: 1.4898. Min Act: -0.0001
Data Index: 736251 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5929. Min Range: -2.5929
Max Act: 1.6016. Min Act: -0.0001
Data Index: 400135 (The Pile)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5929. Min Range: -2.5929
Max Act: 1.4156. Min Act: -0.0001
Data Index: 958808 (The Pile)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5929. Min Range: -2.5929
Max Act: 1.4092. Min Act: -0.0001
Data Index: 1628338 (The Pile)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5929. Min Range: -2.5929
Max Act: 1.4119. Min Act: -0.0001
Data Index: 715186 (The Pile)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5929. Min Range: -2.5929
Max Act: 1.3409. Min Act: -0.0001
Data Index: 1307575 (The Pile)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5929. Min Range: -2.5929
Max Act: 1.4255. Min Act: -0.0001
Data Index: 1226618 (The Pile)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5929. Min Range: -2.5929
Max Act: 1.3034. Min Act: -0.0001
Data Index: 625716 (The Pile)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19