Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1954 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 4.4651. Min Range: -4.4651
Max Act: 4.4651. Min Act: -0.0001
Data Index: 815198 (The Pile)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4651. Min Range: -4.4651
Max Act: 4.4651. Min Act: -0.0001
Data Index: 492667 (The Pile)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4651. Min Range: -4.4651
Max Act: 4.1807. Min Act: -0.0001
Data Index: 1936407 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4651. Min Range: -4.4651
Max Act: 4.1824. Min Act: -0.0001
Data Index: 1036577 (The Pile)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4651. Min Range: -4.4651
Max Act: 3.2441. Min Act: -0.0001
Data Index: 88855 (The Pile)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4651. Min Range: -4.4651
Max Act: 3.3976. Min Act: -0.0001
Data Index: 1871556 (The Pile)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4651. Min Range: -4.4651
Max Act: 3.7013. Min Act: -0.0001
Data Index: 1936227 (The Pile)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4651. Min Range: -4.4651
Max Act: 3.3781. Min Act: -0.0000
Data Index: 642567 (The Pile)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4651. Min Range: -4.4651
Max Act: 3.6062. Min Act: -0.0000
Data Index: 1001729 (The Pile)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4651. Min Range: -4.4651
Max Act: 3.4263. Min Act: -0.0000
Data Index: 1170226 (The Pile)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4651. Min Range: -4.4651
Max Act: 3.1082. Min Act: -0.0001
Data Index: 979575 (The Pile)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4651. Min Range: -4.4651
Max Act: 2.9373. Min Act: -0.0001
Data Index: 598783 (The Pile)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4651. Min Range: -4.4651
Max Act: 3.5542. Min Act: -0.0001
Data Index: 1832055 (The Pile)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4651. Min Range: -4.4651
Max Act: 3.3318. Min Act: -0.0001
Data Index: 386413 (The Pile)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4651. Min Range: -4.4651
Max Act: 3.0926. Min Act: -0.0000
Data Index: 644761 (The Pile)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4651. Min Range: -4.4651
Max Act: 3.2933. Min Act: -0.0000
Data Index: 619373 (The Pile)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4651. Min Range: -4.4651
Max Act: 3.2318. Min Act: -0.0000
Data Index: 94153 (The Pile)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4651. Min Range: -4.4651
Max Act: 3.3522. Min Act: -0.0000
Data Index: 146840 (The Pile)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4651. Min Range: -4.4651
Max Act: 3.0045. Min Act: -0.0000
Data Index: 1681847 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4651. Min Range: -4.4651
Max Act: 3.1461. Min Act: -0.0001
Data Index: 1301166 (The Pile)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19