Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 187 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.5522. Min Range: -1.5522
Max Act: 1.5522. Min Act: -0.0001
Data Index: 921679 (The Pile)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5522. Min Range: -1.5522
Max Act: 1.4111. Min Act: -0.0001
Data Index: 1510307 (The Pile)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5522. Min Range: -1.5522
Max Act: 1.3313. Min Act: -0.0001
Data Index: 109388 (The Pile)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5522. Min Range: -1.5522
Max Act: 1.2912. Min Act: -0.0001
Data Index: 1144437 (The Pile)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5522. Min Range: -1.5522
Max Act: 1.3873. Min Act: -0.0001
Data Index: 1122685 (The Pile)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5522. Min Range: -1.5522
Max Act: 1.3043. Min Act: -0.0001
Data Index: 1026011 (The Pile)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5522. Min Range: -1.5522
Max Act: 1.2138. Min Act: -0.0001
Data Index: 1204840 (The Pile)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5522. Min Range: -1.5522
Max Act: 1.3109. Min Act: -0.0001
Data Index: 201473 (The Pile)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5522. Min Range: -1.5522
Max Act: 1.2855. Min Act: -0.0001
Data Index: 1540512 (The Pile)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5522. Min Range: -1.5522
Max Act: 1.1786. Min Act: -0.0001
Data Index: 1235458 (The Pile)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5522. Min Range: -1.5522
Max Act: 1.2462. Min Act: -0.0001
Data Index: 1871327 (The Pile)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5522. Min Range: -1.5522
Max Act: 1.2317. Min Act: -0.0001
Data Index: 741670 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5522. Min Range: -1.5522
Max Act: 1.2824. Min Act: -0.0001
Data Index: 989281 (The Pile)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5522. Min Range: -1.5522
Max Act: 1.2245. Min Act: -0.0001
Data Index: 384825 (The Pile)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5522. Min Range: -1.5522
Max Act: 1.2842. Min Act: -0.0001
Data Index: 1031943 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5522. Min Range: -1.5522
Max Act: 1.1899. Min Act: -0.0001
Data Index: 1796871 (The Pile)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5522. Min Range: -1.5522
Max Act: 1.2579. Min Act: -0.0001
Data Index: 1606525 (The Pile)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5522. Min Range: -1.5522
Max Act: 1.1234. Min Act: -0.0001
Data Index: 1731411 (The Pile)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5522. Min Range: -1.5522
Max Act: 1.2268. Min Act: -0.0001
Data Index: 1886895 (The Pile)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5522. Min Range: -1.5522
Max Act: 1.2225. Min Act: -0.0001
Data Index: 1995646 (The Pile)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19