Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1987 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 6.4796. Min Range: -6.4796
Max Act: 6.4648. Min Act: -0.0000
Data Index: 1866379 (The Pile)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4796. Min Range: -6.4796
Max Act: 6.4796. Min Act: 0.0000
Data Index: 1951028 (The Pile)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4796. Min Range: -6.4796
Max Act: 6.1640. Min Act: -0.0000
Data Index: 1399654 (The Pile)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4796. Min Range: -6.4796
Max Act: 6.2311. Min Act: -0.0000
Data Index: 425190 (The Pile)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4796. Min Range: -6.4796
Max Act: 5.9526. Min Act: -0.0000
Data Index: 1891129 (The Pile)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4796. Min Range: -6.4796
Max Act: 5.9180. Min Act: -0.0000
Data Index: 693502 (The Pile)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4796. Min Range: -6.4796
Max Act: 6.1123. Min Act: -0.0000
Data Index: 216356 (The Pile)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4796. Min Range: -6.4796
Max Act: 6.1277. Min Act: -0.0000
Data Index: 970611 (The Pile)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4796. Min Range: -6.4796
Max Act: 5.8190. Min Act: 0.0000
Data Index: 1762519 (The Pile)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4796. Min Range: -6.4796
Max Act: 5.9921. Min Act: -0.0000
Data Index: 1397803 (The Pile)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4796. Min Range: -6.4796
Max Act: 5.7773. Min Act: -0.0000
Data Index: 341095 (The Pile)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4796. Min Range: -6.4796
Max Act: 5.7200. Min Act: -0.0000
Data Index: 82345 (The Pile)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4796. Min Range: -6.4796
Max Act: 5.2512. Min Act: -0.0000
Data Index: 1553215 (The Pile)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4796. Min Range: -6.4796
Max Act: 5.7613. Min Act: -0.0000
Data Index: 767774 (The Pile)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4796. Min Range: -6.4796
Max Act: 5.7224. Min Act: 0.0000
Data Index: 773296 (The Pile)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4796. Min Range: -6.4796
Max Act: 5.5232. Min Act: 0.0000
Data Index: 620262 (The Pile)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4796. Min Range: -6.4796
Max Act: 5.5079. Min Act: 0.0000
Data Index: 493971 (The Pile)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4796. Min Range: -6.4796
Max Act: 5.5114. Min Act: -0.0000
Data Index: 1675337 (The Pile)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4796. Min Range: -6.4796
Max Act: 5.3910. Min Act: -0.0000
Data Index: 989179 (The Pile)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4796. Min Range: -6.4796
Max Act: 5.5697. Min Act: -0.0000
Data Index: 1396698 (The Pile)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19