Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3129 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 4.6365. Min Range: -4.6365
Max Act: 4.6365. Min Act: -0.0001
Data Index: 190345 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6365. Min Range: -4.6365
Max Act: 4.1019. Min Act: -0.0001
Data Index: 948877 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6365. Min Range: -4.6365
Max Act: 4.0042. Min Act: -0.0001
Data Index: 127219 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6365. Min Range: -4.6365
Max Act: 3.9885. Min Act: -0.0001
Data Index: 313447 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6365. Min Range: -4.6365
Max Act: 3.7995. Min Act: -0.0001
Data Index: 143909 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6365. Min Range: -4.6365
Max Act: 3.7376. Min Act: -0.0001
Data Index: 1010556 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6365. Min Range: -4.6365
Max Act: 3.7690. Min Act: -0.0001
Data Index: 263550 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6365. Min Range: -4.6365
Max Act: 3.5815. Min Act: -0.0001
Data Index: 952401 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6365. Min Range: -4.6365
Max Act: 3.8487. Min Act: -0.0001
Data Index: 366246 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6365. Min Range: -4.6365
Max Act: 3.6715. Min Act: -0.0001
Data Index: 427651 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6365. Min Range: -4.6365
Max Act: 3.6448. Min Act: -0.0001
Data Index: 1230540 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6365. Min Range: -4.6365
Max Act: 3.8008. Min Act: -0.0001
Data Index: 514987 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6365. Min Range: -4.6365
Max Act: 3.7784. Min Act: -0.0001
Data Index: 949584 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6365. Min Range: -4.6365
Max Act: 3.5115. Min Act: -0.0001
Data Index: 713989 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6365. Min Range: -4.6365
Max Act: 3.6345. Min Act: -0.0001
Data Index: 421377 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6365. Min Range: -4.6365
Max Act: 3.7908. Min Act: -0.0001
Data Index: 66832 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6365. Min Range: -4.6365
Max Act: 3.7629. Min Act: -0.0001
Data Index: 625962 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6365. Min Range: -4.6365
Max Act: 3.5868. Min Act: -0.0001
Data Index: 396102 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6365. Min Range: -4.6365
Max Act: 3.5792. Min Act: -0.0001
Data Index: 1027192 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6365. Min Range: -4.6365
Max Act: 3.5645. Min Act: -0.0001
Data Index: 1313647 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19