Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2759 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.0411. Min Range: -1.0411
Max Act: 1.0345. Min Act: -0.0001
Data Index: 459864 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0411. Min Range: -1.0411
Max Act: 1.0071. Min Act: -0.0001
Data Index: 248480 (C4 (Web Text))
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0411. Min Range: -1.0411
Max Act: 1.0298. Min Act: -0.0001
Data Index: 217535 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0411. Min Range: -1.0411
Max Act: 0.9671. Min Act: -0.0001
Data Index: 1644841 (Python Code)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0411. Min Range: -1.0411
Max Act: 1.0411. Min Act: -0.0001
Data Index: 300123 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0411. Min Range: -1.0411
Max Act: 1.0240. Min Act: -0.0001
Data Index: 1231819 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0411. Min Range: -1.0411
Max Act: 0.9238. Min Act: -0.0001
Data Index: 1206846 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0411. Min Range: -1.0411
Max Act: 0.8958. Min Act: -0.0001
Data Index: 1099933 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0411. Min Range: -1.0411
Max Act: 0.8489. Min Act: -0.0001
Data Index: 637633 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0411. Min Range: -1.0411
Max Act: 0.8438. Min Act: -0.0001
Data Index: 1282308 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0411. Min Range: -1.0411
Max Act: 0.8217. Min Act: -0.0001
Data Index: 180137 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0411. Min Range: -1.0411
Max Act: 0.8538. Min Act: -0.0001
Data Index: 668741 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0411. Min Range: -1.0411
Max Act: 0.8503. Min Act: -0.0001
Data Index: 573155 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0411. Min Range: -1.0411
Max Act: 0.7395. Min Act: -0.0001
Data Index: 697502 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0411. Min Range: -1.0411
Max Act: 0.7562. Min Act: -0.0001
Data Index: 422365 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0411. Min Range: -1.0411
Max Act: 0.7790. Min Act: -0.0001
Data Index: 1060263 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0411. Min Range: -1.0411
Max Act: 0.8449. Min Act: -0.0001
Data Index: 710141 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0411. Min Range: -1.0411
Max Act: 0.8712. Min Act: -0.0001
Data Index: 821146 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0411. Min Range: -1.0411
Max Act: 0.8634. Min Act: -0.0001
Data Index: 637263 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0411. Min Range: -1.0411
Max Act: 0.8101. Min Act: -0.0001
Data Index: 1021833 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19