Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4810 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.1896. Min Range: -1.1896
Max Act: 1.1231. Min Act: -0.0001
Data Index: 548096 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1896. Min Range: -1.1896
Max Act: 1.1896. Min Act: -0.0001
Data Index: 86095 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1896. Min Range: -1.1896
Max Act: 1.1555. Min Act: -0.0001
Data Index: 909338 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1896. Min Range: -1.1896
Max Act: 1.1149. Min Act: -0.0001
Data Index: 795774 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1896. Min Range: -1.1896
Max Act: 1.0326. Min Act: -0.0001
Data Index: 639552 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1896. Min Range: -1.1896
Max Act: 1.0988. Min Act: -0.0001
Data Index: 1349158 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1896. Min Range: -1.1896
Max Act: 0.9611. Min Act: -0.0001
Data Index: 1343741 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1896. Min Range: -1.1896
Max Act: 1.0374. Min Act: -0.0001
Data Index: 232326 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1896. Min Range: -1.1896
Max Act: 0.9687. Min Act: -0.0001
Data Index: 175403 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1896. Min Range: -1.1896
Max Act: 1.0414. Min Act: -0.0001
Data Index: 1077431 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1896. Min Range: -1.1896
Max Act: 1.0220. Min Act: -0.0001
Data Index: 970860 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1896. Min Range: -1.1896
Max Act: 0.9772. Min Act: -0.0001
Data Index: 1358549 (C4 (Web Text))
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1896. Min Range: -1.1896
Max Act: 0.9990. Min Act: -0.0001
Data Index: 1233524 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1896. Min Range: -1.1896
Max Act: 1.0067. Min Act: -0.0000
Data Index: 1306969 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1896. Min Range: -1.1896
Max Act: 0.9305. Min Act: -0.0001
Data Index: 650005 (C4 (Web Text))
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1896. Min Range: -1.1896
Max Act: 0.9696. Min Act: -0.0001
Data Index: 1156737 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1896. Min Range: -1.1896
Max Act: 0.9014. Min Act: -0.0001
Data Index: 523694 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1896. Min Range: -1.1896
Max Act: 0.9870. Min Act: -0.0001
Data Index: 293054 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1896. Min Range: -1.1896
Max Act: 0.9672. Min Act: -0.0001
Data Index: 277303 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1896. Min Range: -1.1896
Max Act: 0.8965. Min Act: -0.0001
Data Index: 804896 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19