Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2683 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.8630. Min Range: -1.8630
Max Act: 1.8630. Min Act: -0.0001
Data Index: 932206 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8630. Min Range: -1.8630
Max Act: 1.8480. Min Act: -0.0001
Data Index: 108276 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8630. Min Range: -1.8630
Max Act: 1.8297. Min Act: -0.0001
Data Index: 1024973 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8630. Min Range: -1.8630
Max Act: 1.6893. Min Act: -0.0001
Data Index: 635479 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8630. Min Range: -1.8630
Max Act: 1.5994. Min Act: -0.0001
Data Index: 733858 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8630. Min Range: -1.8630
Max Act: 1.7819. Min Act: -0.0001
Data Index: 204225 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8630. Min Range: -1.8630
Max Act: 1.8630. Min Act: -0.0001
Data Index: 899560 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8630. Min Range: -1.8630
Max Act: 1.5471. Min Act: -0.0001
Data Index: 405469 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8630. Min Range: -1.8630
Max Act: 1.6340. Min Act: -0.0001
Data Index: 1355380 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8630. Min Range: -1.8630
Max Act: 1.7247. Min Act: -0.0001
Data Index: 1249152 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8630. Min Range: -1.8630
Max Act: 1.6826. Min Act: -0.0001
Data Index: 1077726 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8630. Min Range: -1.8630
Max Act: 1.7540. Min Act: -0.0001
Data Index: 1010546 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8630. Min Range: -1.8630
Max Act: 1.6506. Min Act: -0.0001
Data Index: 1009207 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8630. Min Range: -1.8630
Max Act: 1.5345. Min Act: -0.0001
Data Index: 1008960 (C4 (Web Text))
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8630. Min Range: -1.8630
Max Act: 1.7119. Min Act: -0.0001
Data Index: 424235 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8630. Min Range: -1.8630
Max Act: 1.6008. Min Act: -0.0001
Data Index: 600185 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8630. Min Range: -1.8630
Max Act: 1.5960. Min Act: -0.0001
Data Index: 392623 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8630. Min Range: -1.8630
Max Act: 1.6530. Min Act: -0.0001
Data Index: 277599 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8630. Min Range: -1.8630
Max Act: 1.5551. Min Act: -0.0001
Data Index: 1271863 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8630. Min Range: -1.8630
Max Act: 1.5314. Min Act: -0.0001
Data Index: 788103 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #19