Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3060 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 1.9853. Min Range: -1.9853
Max Act: 1.9853. Min Act: -0.0003
Data Index: 505191 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9853. Min Range: -1.9853
Max Act: 1.8684. Min Act: -0.0003
Data Index: 1310431 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9853. Min Range: -1.9853
Max Act: 1.7113. Min Act: -0.0003
Data Index: 573741 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9853. Min Range: -1.9853
Max Act: 1.5979. Min Act: -0.0003
Data Index: 51968 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9853. Min Range: -1.9853
Max Act: 1.4984. Min Act: -0.0003
Data Index: 195560 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9853. Min Range: -1.9853
Max Act: 1.3851. Min Act: -0.0003
Data Index: 1241469 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9853. Min Range: -1.9853
Max Act: 1.5326. Min Act: -0.0003
Data Index: 1052762 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9853. Min Range: -1.9853
Max Act: 1.4910. Min Act: -0.0003
Data Index: 542584 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9853. Min Range: -1.9853
Max Act: 1.5603. Min Act: -0.0003
Data Index: 1130566 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9853. Min Range: -1.9853
Max Act: 1.3985. Min Act: -0.0003
Data Index: 1143456 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9853. Min Range: -1.9853
Max Act: 1.4269. Min Act: -0.0003
Data Index: 467643 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9853. Min Range: -1.9853
Max Act: 1.3643. Min Act: -0.0003
Data Index: 1145850 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9853. Min Range: -1.9853
Max Act: 1.3950. Min Act: -0.0003
Data Index: 318494 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9853. Min Range: -1.9853
Max Act: 1.3577. Min Act: -0.0003
Data Index: 302334 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9853. Min Range: -1.9853
Max Act: 1.4037. Min Act: -0.0003
Data Index: 309461 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9853. Min Range: -1.9853
Max Act: 1.3090. Min Act: -0.0003
Data Index: 1100651 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9853. Min Range: -1.9853
Max Act: 1.3368. Min Act: -0.0003
Data Index: 878918 (C4 (Web Text))
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9853. Min Range: -1.9853
Max Act: 1.3282. Min Act: -0.0003
Data Index: 60368 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9853. Min Range: -1.9853
Max Act: 1.3706. Min Act: -0.0003
Data Index: 62173 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9853. Min Range: -1.9853
Max Act: 1.3641. Min Act: -0.0003
Data Index: 1061306 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19