Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2698 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 5.2844. Min Range: -5.2844
Max Act: 5.2844. Min Act: -0.0001
Data Index: 314454 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2844. Min Range: -5.2844
Max Act: 4.9711. Min Act: -0.0001
Data Index: 84283 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2844. Min Range: -5.2844
Max Act: 5.1128. Min Act: -0.0001
Data Index: 1087623 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2844. Min Range: -5.2844
Max Act: 4.9245. Min Act: -0.0001
Data Index: 334983 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2844. Min Range: -5.2844
Max Act: 4.7048. Min Act: -0.0001
Data Index: 45772 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2844. Min Range: -5.2844
Max Act: 4.6791. Min Act: -0.0001
Data Index: 885888 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2844. Min Range: -5.2844
Max Act: 4.3935. Min Act: -0.0001
Data Index: 1213809 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2844. Min Range: -5.2844
Max Act: 4.4030. Min Act: -0.0001
Data Index: 400594 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2844. Min Range: -5.2844
Max Act: 4.8127. Min Act: -0.0001
Data Index: 152942 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2844. Min Range: -5.2844
Max Act: 4.0226. Min Act: -0.0001
Data Index: 348255 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2844. Min Range: -5.2844
Max Act: 4.1152. Min Act: -0.0001
Data Index: 322379 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2844. Min Range: -5.2844
Max Act: 4.0975. Min Act: -0.0001
Data Index: 579255 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2844. Min Range: -5.2844
Max Act: 3.6424. Min Act: -0.0001
Data Index: 1297922 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2844. Min Range: -5.2844
Max Act: 4.2876. Min Act: -0.0001
Data Index: 1160095 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2844. Min Range: -5.2844
Max Act: 3.7493. Min Act: -0.0001
Data Index: 1231091 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2844. Min Range: -5.2844
Max Act: 4.2205. Min Act: -0.0001
Data Index: 229606 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2844. Min Range: -5.2844
Max Act: 4.0714. Min Act: -0.0001
Data Index: 997328 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2844. Min Range: -5.2844
Max Act: 4.0415. Min Act: -0.0001
Data Index: 407459 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2844. Min Range: -5.2844
Max Act: 3.8813. Min Act: -0.0001
Data Index: 1275789 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2844. Min Range: -5.2844
Max Act: 3.8773. Min Act: -0.0001
Data Index: 1140194 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19