Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 3789 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.7579. Min Range: -1.7579
Max Act: 1.6443. Min Act: -0.0001
Data Index: 1394969 (The Pile)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7579. Min Range: -1.7579
Max Act: 1.7579. Min Act: -0.0001
Data Index: 1145525 (The Pile)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7579. Min Range: -1.7579
Max Act: 1.5370. Min Act: -0.0001
Data Index: 1395378 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7579. Min Range: -1.7579
Max Act: 1.4572. Min Act: -0.0001
Data Index: 391090 (The Pile)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7579. Min Range: -1.7579
Max Act: 1.4324. Min Act: -0.0001
Data Index: 1388812 (The Pile)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7579. Min Range: -1.7579
Max Act: 1.4017. Min Act: -0.0001
Data Index: 1533034 (The Pile)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7579. Min Range: -1.7579
Max Act: 1.4739. Min Act: -0.0001
Data Index: 412913 (The Pile)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7579. Min Range: -1.7579
Max Act: 1.4568. Min Act: -0.0001
Data Index: 1086755 (The Pile)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7579. Min Range: -1.7579
Max Act: 1.4133. Min Act: -0.0001
Data Index: 1688412 (The Pile)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7579. Min Range: -1.7579
Max Act: 1.4096. Min Act: -0.0001
Data Index: 572779 (The Pile)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7579. Min Range: -1.7579
Max Act: 1.3523. Min Act: -0.0001
Data Index: 705830 (The Pile)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7579. Min Range: -1.7579
Max Act: 1.3968. Min Act: -0.0001
Data Index: 912037 (The Pile)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7579. Min Range: -1.7579
Max Act: 1.2379. Min Act: -0.0001
Data Index: 107552 (The Pile)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7579. Min Range: -1.7579
Max Act: 1.3504. Min Act: -0.0001
Data Index: 167067 (The Pile)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7579. Min Range: -1.7579
Max Act: 1.3579. Min Act: -0.0001
Data Index: 845315 (The Pile)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7579. Min Range: -1.7579
Max Act: 1.3985. Min Act: -0.0001
Data Index: 1629141 (The Pile)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7579. Min Range: -1.7579
Max Act: 1.3490. Min Act: -0.0001
Data Index: 766388 (The Pile)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7579. Min Range: -1.7579
Max Act: 1.2910. Min Act: -0.0001
Data Index: 369178 (The Pile)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7579. Min Range: -1.7579
Max Act: 1.2647. Min Act: -0.0001
Data Index: 1308756 (The Pile)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7579. Min Range: -1.7579
Max Act: 1.2867. Min Act: -0.0001
Data Index: 932522 (The Pile)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19