Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 659 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 4.5930. Min Range: -4.5930
Max Act: 4.4885. Min Act: -0.0001
Data Index: 1472426 (The Pile)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5930. Min Range: -4.5930
Max Act: 4.3615. Min Act: -0.0001
Data Index: 824706 (The Pile)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5930. Min Range: -4.5930
Max Act: 4.5930. Min Act: -0.0001
Data Index: 414605 (The Pile)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5930. Min Range: -4.5930
Max Act: 4.5545. Min Act: -0.0001
Data Index: 631793 (The Pile)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5930. Min Range: -4.5930
Max Act: 4.4803. Min Act: -0.0001
Data Index: 1855152 (The Pile)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5930. Min Range: -4.5930
Max Act: 4.4320. Min Act: -0.0001
Data Index: 1030826 (The Pile)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5930. Min Range: -4.5930
Max Act: 4.2477. Min Act: -0.0001
Data Index: 652197 (The Pile)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5930. Min Range: -4.5930
Max Act: 3.9810. Min Act: -0.0001
Data Index: 658 (The Pile)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5930. Min Range: -4.5930
Max Act: 4.3045. Min Act: -0.0001
Data Index: 363709 (The Pile)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5930. Min Range: -4.5930
Max Act: 4.1123. Min Act: -0.0001
Data Index: 1076554 (The Pile)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5930. Min Range: -4.5930
Max Act: 4.2149. Min Act: -0.0001
Data Index: 557571 (The Pile)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5930. Min Range: -4.5930
Max Act: 4.0366. Min Act: -0.0001
Data Index: 1049691 (The Pile)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5930. Min Range: -4.5930
Max Act: 4.1408. Min Act: -0.0001
Data Index: 1612918 (The Pile)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5930. Min Range: -4.5930
Max Act: 4.2827. Min Act: -0.0001
Data Index: 316761 (The Pile)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5930. Min Range: -4.5930
Max Act: 3.9835. Min Act: -0.0001
Data Index: 1758672 (The Pile)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5930. Min Range: -4.5930
Max Act: 4.1353. Min Act: -0.0001
Data Index: 437952 (The Pile)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5930. Min Range: -4.5930
Max Act: 3.9456. Min Act: -0.0001
Data Index: 1066005 (The Pile)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5930. Min Range: -4.5930
Max Act: 4.2293. Min Act: -0.0001
Data Index: 249919 (The Pile)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5930. Min Range: -4.5930
Max Act: 3.9021. Min Act: -0.0001
Data Index: 1266169 (The Pile)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5930. Min Range: -4.5930
Max Act: 4.0191. Min Act: -0.0001
Data Index: 504327 (The Pile)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19