Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2624 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.4844. Min Range: -1.4844
Max Act: 1.4844. Min Act: -0.0001
Data Index: 556307 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4844. Min Range: -1.4844
Max Act: 1.3439. Min Act: -0.0001
Data Index: 1318223 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4844. Min Range: -1.4844
Max Act: 1.3409. Min Act: -0.0001
Data Index: 204060 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4844. Min Range: -1.4844
Max Act: 1.2506. Min Act: -0.0001
Data Index: 31673 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4844. Min Range: -1.4844
Max Act: 1.1891. Min Act: -0.0001
Data Index: 530468 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4844. Min Range: -1.4844
Max Act: 1.2265. Min Act: -0.0001
Data Index: 30898 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4844. Min Range: -1.4844
Max Act: 1.1969. Min Act: -0.0001
Data Index: 839201 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4844. Min Range: -1.4844
Max Act: 1.1581. Min Act: -0.0001
Data Index: 557466 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4844. Min Range: -1.4844
Max Act: 1.1558. Min Act: -0.0001
Data Index: 767447 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4844. Min Range: -1.4844
Max Act: 1.1954. Min Act: -0.0001
Data Index: 604827 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4844. Min Range: -1.4844
Max Act: 1.1473. Min Act: -0.0001
Data Index: 179007 (C4 (Web Text))
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4844. Min Range: -1.4844
Max Act: 1.1263. Min Act: -0.0001
Data Index: 57754 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4844. Min Range: -1.4844
Max Act: 1.1885. Min Act: -0.0001
Data Index: 359249 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4844. Min Range: -1.4844
Max Act: 1.1237. Min Act: -0.0001
Data Index: 1050896 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4844. Min Range: -1.4844
Max Act: 1.1314. Min Act: -0.0001
Data Index: 1148982 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4844. Min Range: -1.4844
Max Act: 1.1810. Min Act: -0.0001
Data Index: 999851 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4844. Min Range: -1.4844
Max Act: 1.1131. Min Act: -0.0001
Data Index: 729955 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4844. Min Range: -1.4844
Max Act: 1.1799. Min Act: -0.0001
Data Index: 104026 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4844. Min Range: -1.4844
Max Act: 1.1393. Min Act: -0.0001
Data Index: 366802 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4844. Min Range: -1.4844
Max Act: 1.1096. Min Act: -0.0001
Data Index: 642956 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19