Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 646 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.4713. Min Range: -2.4713
Max Act: 2.4713. Min Act: -0.0002
Data Index: 438394 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4713. Min Range: -2.4713
Max Act: 2.2751. Min Act: -0.0001
Data Index: 57675 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4713. Min Range: -2.4713
Max Act: 2.3201. Min Act: -0.0001
Data Index: 386636 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4713. Min Range: -2.4713
Max Act: 2.0088. Min Act: -0.0001
Data Index: 818854 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4713. Min Range: -2.4713
Max Act: 2.1379. Min Act: -0.0002
Data Index: 6171 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4713. Min Range: -2.4713
Max Act: 2.0782. Min Act: -0.0002
Data Index: 811543 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4713. Min Range: -2.4713
Max Act: 1.9193. Min Act: -0.0001
Data Index: 1127138 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4713. Min Range: -2.4713
Max Act: 2.0989. Min Act: -0.0002
Data Index: 783708 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4713. Min Range: -2.4713
Max Act: 2.2067. Min Act: -0.0002
Data Index: 1261497 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4713. Min Range: -2.4713
Max Act: 2.0019. Min Act: -0.0001
Data Index: 30287 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4713. Min Range: -2.4713
Max Act: 1.9492. Min Act: -0.0001
Data Index: 692711 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4713. Min Range: -2.4713
Max Act: 1.7982. Min Act: -0.0001
Data Index: 532318 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4713. Min Range: -2.4713
Max Act: 1.8850. Min Act: -0.0002
Data Index: 681417 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4713. Min Range: -2.4713
Max Act: 1.9782. Min Act: -0.0002
Data Index: 63617 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4713. Min Range: -2.4713
Max Act: 1.9055. Min Act: -0.0002
Data Index: 182711 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4713. Min Range: -2.4713
Max Act: 1.7287. Min Act: -0.0001
Data Index: 1332344 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4713. Min Range: -2.4713
Max Act: 1.8349. Min Act: -0.0001
Data Index: 840759 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4713. Min Range: -2.4713
Max Act: 1.8142. Min Act: -0.0002
Data Index: 938253 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4713. Min Range: -2.4713
Max Act: 1.7983. Min Act: -0.0001
Data Index: 93012 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4713. Min Range: -2.4713
Max Act: 1.8680. Min Act: -0.0001
Data Index: 509845 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19