Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 507 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.7008. Min Range: -1.7008
Max Act: 1.6321. Min Act: -0.0000
Data Index: 463145 (The Pile)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7008. Min Range: -1.7008
Max Act: 1.6018. Min Act: -0.0001
Data Index: 1875567 (The Pile)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7008. Min Range: -1.7008
Max Act: 1.5357. Min Act: -0.0000
Data Index: 1693356 (The Pile)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7008. Min Range: -1.7008
Max Act: 1.5705. Min Act: -0.0001
Data Index: 690370 (The Pile)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7008. Min Range: -1.7008
Max Act: 1.7008. Min Act: -0.0001
Data Index: 961758 (The Pile)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7008. Min Range: -1.7008
Max Act: 1.6384. Min Act: -0.0001
Data Index: 102409 (The Pile)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7008. Min Range: -1.7008
Max Act: 1.5347. Min Act: -0.0001
Data Index: 564738 (The Pile)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7008. Min Range: -1.7008
Max Act: 1.6080. Min Act: -0.0001
Data Index: 1563777 (The Pile)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7008. Min Range: -1.7008
Max Act: 1.5185. Min Act: -0.0001
Data Index: 672913 (The Pile)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7008. Min Range: -1.7008
Max Act: 1.4341. Min Act: -0.0001
Data Index: 1922532 (The Pile)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7008. Min Range: -1.7008
Max Act: 1.5060. Min Act: -0.0001
Data Index: 1445160 (The Pile)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7008. Min Range: -1.7008
Max Act: 1.4310. Min Act: -0.0001
Data Index: 1932101 (The Pile)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7008. Min Range: -1.7008
Max Act: 1.4030. Min Act: -0.0001
Data Index: 1027164 (The Pile)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7008. Min Range: -1.7008
Max Act: 1.4911. Min Act: -0.0000
Data Index: 371311 (The Pile)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7008. Min Range: -1.7008
Max Act: 1.4913. Min Act: -0.0001
Data Index: 192135 (The Pile)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7008. Min Range: -1.7008
Max Act: 1.4887. Min Act: -0.0001
Data Index: 817329 (The Pile)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7008. Min Range: -1.7008
Max Act: 1.4615. Min Act: -0.0001
Data Index: 398174 (The Pile)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7008. Min Range: -1.7008
Max Act: 1.3970. Min Act: -0.0001
Data Index: 327487 (The Pile)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7008. Min Range: -1.7008
Max Act: 1.5354. Min Act: -0.0001
Data Index: 1279751 (The Pile)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7008. Min Range: -1.7008
Max Act: 1.4545. Min Act: -0.0001
Data Index: 329623 (The Pile)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19