Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4700 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.6141. Min Range: -2.6141
Max Act: 2.5643. Min Act: -0.0000
Data Index: 620311 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6141. Min Range: -2.6141
Max Act: 2.6141. Min Act: -0.0001
Data Index: 249389 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6141. Min Range: -2.6141
Max Act: 2.3212. Min Act: -0.0001
Data Index: 73509 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6141. Min Range: -2.6141
Max Act: 2.3254. Min Act: -0.0001
Data Index: 219396 (C4 (Web Text))
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6141. Min Range: -2.6141
Max Act: 2.3001. Min Act: -0.0001
Data Index: 230374 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6141. Min Range: -2.6141
Max Act: 2.5252. Min Act: -0.0001
Data Index: 281562 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6141. Min Range: -2.6141
Max Act: 2.4573. Min Act: -0.0001
Data Index: 1210833 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6141. Min Range: -2.6141
Max Act: 2.4535. Min Act: -0.0001
Data Index: 1102220 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6141. Min Range: -2.6141
Max Act: 2.4145. Min Act: -0.0001
Data Index: 600401 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6141. Min Range: -2.6141
Max Act: 2.2761. Min Act: -0.0001
Data Index: 117255 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6141. Min Range: -2.6141
Max Act: 2.1491. Min Act: -0.0001
Data Index: 656670 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6141. Min Range: -2.6141
Max Act: 1.9109. Min Act: -0.0000
Data Index: 83640 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6141. Min Range: -2.6141
Max Act: 2.0110. Min Act: -0.0001
Data Index: 520843 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6141. Min Range: -2.6141
Max Act: 2.2015. Min Act: -0.0001
Data Index: 1213265 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6141. Min Range: -2.6141
Max Act: 2.0396. Min Act: -0.0001
Data Index: 276875 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6141. Min Range: -2.6141
Max Act: 2.1163. Min Act: -0.0001
Data Index: 331585 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6141. Min Range: -2.6141
Max Act: 1.9953. Min Act: -0.0001
Data Index: 1292055 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6141. Min Range: -2.6141
Max Act: 2.0479. Min Act: -0.0001
Data Index: 873845 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6141. Min Range: -2.6141
Max Act: 1.8396. Min Act: -0.0001
Data Index: 974545 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6141. Min Range: -2.6141
Max Act: 1.9430. Min Act: -0.0001
Data Index: 291913 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #19