Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2629 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.4554. Min Range: -0.4554
Max Act: 0.4406. Min Act: -0.0000
Data Index: 1343654 (The Pile)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4554. Min Range: -0.4554
Max Act: 0.4554. Min Act: -0.0000
Data Index: 576719 (The Pile)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4554. Min Range: -0.4554
Max Act: 0.4140. Min Act: -0.0000
Data Index: 1214586 (The Pile)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4554. Min Range: -0.4554
Max Act: 0.3912. Min Act: -0.0000
Data Index: 1271614 (The Pile)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4554. Min Range: -0.4554
Max Act: 0.4097. Min Act: -0.0000
Data Index: 1377154 (The Pile)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4554. Min Range: -0.4554
Max Act: 0.3786. Min Act: -0.0000
Data Index: 1239064 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4554. Min Range: -0.4554
Max Act: 0.3795. Min Act: -0.0000
Data Index: 1534694 (The Pile)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4554. Min Range: -0.4554
Max Act: 0.3529. Min Act: -0.0000
Data Index: 1484089 (The Pile)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4554. Min Range: -0.4554
Max Act: 0.3367. Min Act: -0.0000
Data Index: 859786 (The Pile)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4554. Min Range: -0.4554
Max Act: 0.3867. Min Act: -0.0000
Data Index: 217810 (The Pile)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4554. Min Range: -0.4554
Max Act: 0.3572. Min Act: -0.0000
Data Index: 262451 (The Pile)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4554. Min Range: -0.4554
Max Act: 0.3649. Min Act: -0.0000
Data Index: 1713959 (The Pile)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4554. Min Range: -0.4554
Max Act: 0.3755. Min Act: -0.0000
Data Index: 1461972 (The Pile)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4554. Min Range: -0.4554
Max Act: 0.2910. Min Act: -0.0000
Data Index: 1522264 (The Pile)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4554. Min Range: -0.4554
Max Act: 0.3294. Min Act: -0.0000
Data Index: 917695 (The Pile)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4554. Min Range: -0.4554
Max Act: 0.3261. Min Act: -0.0000
Data Index: 1460822 (The Pile)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4554. Min Range: -0.4554
Max Act: 0.3418. Min Act: -0.0000
Data Index: 16915 (The Pile)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4554. Min Range: -0.4554
Max Act: 0.3387. Min Act: -0.0000
Data Index: 3524 (The Pile)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4554. Min Range: -0.4554
Max Act: 0.3475. Min Act: -0.0000
Data Index: 1021122 (The Pile)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4554. Min Range: -0.4554
Max Act: 0.3447. Min Act: -0.0000
Data Index: 896941 (The Pile)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #19