Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3465 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.7953. Min Range: -0.7953
Max Act: 0.7953. Min Act: -0.0001
Data Index: 1037004 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7953. Min Range: -0.7953
Max Act: 0.7273. Min Act: -0.0001
Data Index: 361237 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7953. Min Range: -0.7953
Max Act: 0.6517. Min Act: -0.0001
Data Index: 1011703 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7953. Min Range: -0.7953
Max Act: 0.6342. Min Act: -0.0001
Data Index: 229740 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7953. Min Range: -0.7953
Max Act: 0.6623. Min Act: -0.0001
Data Index: 556273 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7953. Min Range: -0.7953
Max Act: 0.6829. Min Act: -0.0001
Data Index: 308412 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7953. Min Range: -0.7953
Max Act: 0.6467. Min Act: -0.0001
Data Index: 961570 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7953. Min Range: -0.7953
Max Act: 0.6170. Min Act: -0.0001
Data Index: 1328215 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7953. Min Range: -0.7953
Max Act: 0.5853. Min Act: -0.0001
Data Index: 394013 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7953. Min Range: -0.7953
Max Act: 0.6177. Min Act: -0.0001
Data Index: 807684 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7953. Min Range: -0.7953
Max Act: 0.5795. Min Act: -0.0001
Data Index: 326824 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7953. Min Range: -0.7953
Max Act: 0.5981. Min Act: -0.0001
Data Index: 436270 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7953. Min Range: -0.7953
Max Act: 0.6167. Min Act: -0.0001
Data Index: 1280116 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7953. Min Range: -0.7953
Max Act: 0.6377. Min Act: -0.0001
Data Index: 1182138 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7953. Min Range: -0.7953
Max Act: 0.5494. Min Act: -0.0001
Data Index: 447792 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7953. Min Range: -0.7953
Max Act: 0.5802. Min Act: -0.0001
Data Index: 1558495 (Python Code)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7953. Min Range: -0.7953
Max Act: 0.5475. Min Act: -0.0001
Data Index: 1136746 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7953. Min Range: -0.7953
Max Act: 0.5842. Min Act: -0.0001
Data Index: 199760 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7953. Min Range: -0.7953
Max Act: 0.6220. Min Act: -0.0001
Data Index: 752789 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7953. Min Range: -0.7953
Max Act: 0.5598. Min Act: -0.0001
Data Index: 1498236 (Python Code)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19