Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 929 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.5923. Min Range: -1.5923
Max Act: 1.4816. Min Act: -0.0000
Data Index: 733059 (The Pile)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5923. Min Range: -1.5923
Max Act: 1.5923. Min Act: -0.0000
Data Index: 713744 (The Pile)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5923. Min Range: -1.5923
Max Act: 1.5236. Min Act: -0.0000
Data Index: 1843826 (The Pile)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5923. Min Range: -1.5923
Max Act: 1.4280. Min Act: -0.0000
Data Index: 1922210 (The Pile)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5923. Min Range: -1.5923
Max Act: 1.3464. Min Act: -0.0000
Data Index: 1814416 (The Pile)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5923. Min Range: -1.5923
Max Act: 1.3357. Min Act: -0.0000
Data Index: 62613 (The Pile)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5923. Min Range: -1.5923
Max Act: 1.3142. Min Act: -0.0000
Data Index: 955881 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5923. Min Range: -1.5923
Max Act: 1.2262. Min Act: -0.0000
Data Index: 1796355 (The Pile)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5923. Min Range: -1.5923
Max Act: 1.2572. Min Act: -0.0000
Data Index: 1677431 (The Pile)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5923. Min Range: -1.5923
Max Act: 1.2865. Min Act: -0.0000
Data Index: 706576 (The Pile)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5923. Min Range: -1.5923
Max Act: 1.2516. Min Act: -0.0000
Data Index: 641109 (The Pile)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5923. Min Range: -1.5923
Max Act: 1.3292. Min Act: -0.0000
Data Index: 435497 (The Pile)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5923. Min Range: -1.5923
Max Act: 1.4062. Min Act: -0.0000
Data Index: 1237481 (The Pile)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5923. Min Range: -1.5923
Max Act: 1.2190. Min Act: -0.0000
Data Index: 1562850 (The Pile)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5923. Min Range: -1.5923
Max Act: 1.2071. Min Act: -0.0000
Data Index: 1045390 (The Pile)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5923. Min Range: -1.5923
Max Act: 1.2371. Min Act: -0.0001
Data Index: 234283 (The Pile)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5923. Min Range: -1.5923
Max Act: 1.2480. Min Act: -0.0000
Data Index: 1093955 (The Pile)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5923. Min Range: -1.5923
Max Act: 1.1913. Min Act: -0.0000
Data Index: 1844222 (The Pile)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5923. Min Range: -1.5923
Max Act: 1.3794. Min Act: -0.0000
Data Index: 394087 (The Pile)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5923. Min Range: -1.5923
Max Act: 1.2266. Min Act: -0.0000
Data Index: 1536340 (The Pile)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19