Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 950 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 2.0613. Min Range: -2.0613
Max Act: 1.9843. Min Act: -0.0001
Data Index: 1276384 (The Pile)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0613. Min Range: -2.0613
Max Act: 1.8627. Min Act: -0.0001
Data Index: 133406 (The Pile)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0613. Min Range: -2.0613
Max Act: 2.0613. Min Act: -0.0001
Data Index: 1818954 (The Pile)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0613. Min Range: -2.0613
Max Act: 1.5300. Min Act: -0.0001
Data Index: 1473714 (The Pile)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0613. Min Range: -2.0613
Max Act: 1.6463. Min Act: -0.0001
Data Index: 726744 (The Pile)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0613. Min Range: -2.0613
Max Act: 1.4928. Min Act: -0.0001
Data Index: 890182 (The Pile)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0613. Min Range: -2.0613
Max Act: 1.4962. Min Act: -0.0001
Data Index: 232488 (The Pile)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0613. Min Range: -2.0613
Max Act: 1.3695. Min Act: -0.0001
Data Index: 1203845 (The Pile)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0613. Min Range: -2.0613
Max Act: 1.5155. Min Act: -0.0001
Data Index: 263213 (The Pile)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0613. Min Range: -2.0613
Max Act: 1.2842. Min Act: -0.0001
Data Index: 1091257 (The Pile)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0613. Min Range: -2.0613
Max Act: 1.5352. Min Act: -0.0001
Data Index: 1868009 (The Pile)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0613. Min Range: -2.0613
Max Act: 1.2745. Min Act: -0.0001
Data Index: 893946 (The Pile)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0613. Min Range: -2.0613
Max Act: 1.5108. Min Act: -0.0001
Data Index: 408015 (The Pile)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0613. Min Range: -2.0613
Max Act: 1.3192. Min Act: -0.0001
Data Index: 165927 (The Pile)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0613. Min Range: -2.0613
Max Act: 1.4257. Min Act: -0.0001
Data Index: 284540 (The Pile)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0613. Min Range: -2.0613
Max Act: 1.4345. Min Act: -0.0001
Data Index: 418063 (The Pile)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0613. Min Range: -2.0613
Max Act: 1.1859. Min Act: -0.0001
Data Index: 1196181 (The Pile)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0613. Min Range: -2.0613
Max Act: 1.3468. Min Act: -0.0001
Data Index: 417964 (The Pile)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0613. Min Range: -2.0613
Max Act: 1.3086. Min Act: -0.0001
Data Index: 1404564 (The Pile)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0613. Min Range: -2.0613
Max Act: 1.3114. Min Act: -0.0001
Data Index: 1716621 (The Pile)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #19