Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1374 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.7537. Min Act: 0.0000
Data Index: 1734240 (The Pile)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.5009. Min Act: -0.0000
Data Index: 267891 (The Pile)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.5023. Min Act: -0.0000
Data Index: 1672614 (The Pile)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.4725. Min Act: -0.0000
Data Index: 963900 (The Pile)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.3192. Min Act: -0.0000
Data Index: 1751712 (The Pile)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.4706. Min Act: -0.0000
Data Index: 1818021 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.4447. Min Act: -0.0000
Data Index: 861675 (The Pile)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.4314. Min Act: -0.0000
Data Index: 1149499 (The Pile)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.2981. Min Act: -0.0000
Data Index: 1278472 (The Pile)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.3868. Min Act: 0.0000
Data Index: 929628 (The Pile)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.3602. Min Act: -0.0000
Data Index: 238285 (The Pile)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.3671. Min Act: -0.0000
Data Index: 1511098 (The Pile)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.2716. Min Act: -0.0000
Data Index: 1305062 (The Pile)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.2411. Min Act: -0.0000
Data Index: 1822344 (The Pile)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.4048. Min Act: -0.0000
Data Index: 1231817 (The Pile)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.2438. Min Act: -0.0000
Data Index: 913532 (The Pile)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.3017. Min Act: -0.0000
Data Index: 899322 (The Pile)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.2182. Min Act: -0.0000
Data Index: 1837921 (The Pile)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.2956. Min Act: 0.0001
Data Index: 314079 (The Pile)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.2249. Min Act: -0.0000
Data Index: 145956 (The Pile)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19