Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1436 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.8680. Min Range: -2.8680
Max Act: 2.8680. Min Act: -0.0000
Data Index: 1353228 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8680. Min Range: -2.8680
Max Act: 2.7090. Min Act: -0.0001
Data Index: 1000430 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8680. Min Range: -2.8680
Max Act: 2.4700. Min Act: -0.0001
Data Index: 126575 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8680. Min Range: -2.8680
Max Act: 2.3077. Min Act: -0.0000
Data Index: 928602 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8680. Min Range: -2.8680
Max Act: 2.2721. Min Act: -0.0000
Data Index: 879079 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8680. Min Range: -2.8680
Max Act: 2.1250. Min Act: -0.0001
Data Index: 57263 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8680. Min Range: -2.8680
Max Act: 2.0882. Min Act: -0.0001
Data Index: 1356114 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8680. Min Range: -2.8680
Max Act: 2.0769. Min Act: -0.0001
Data Index: 753038 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8680. Min Range: -2.8680
Max Act: 1.9388. Min Act: -0.0001
Data Index: 1091660 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8680. Min Range: -2.8680
Max Act: 1.8003. Min Act: -0.0001
Data Index: 268121 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8680. Min Range: -2.8680
Max Act: 1.8887. Min Act: -0.0001
Data Index: 53534 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8680. Min Range: -2.8680
Max Act: 1.9121. Min Act: -0.0001
Data Index: 381037 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8680. Min Range: -2.8680
Max Act: 1.8076. Min Act: -0.0001
Data Index: 528312 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8680. Min Range: -2.8680
Max Act: 1.6027. Min Act: -0.0001
Data Index: 732963 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8680. Min Range: -2.8680
Max Act: 1.7729. Min Act: -0.0001
Data Index: 1357472 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8680. Min Range: -2.8680
Max Act: 1.5888. Min Act: -0.0001
Data Index: 1047281 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8680. Min Range: -2.8680
Max Act: 1.8598. Min Act: -0.0001
Data Index: 563165 (C4 (Web Text))
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8680. Min Range: -2.8680
Max Act: 1.6830. Min Act: -0.0001
Data Index: 830631 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8680. Min Range: -2.8680
Max Act: 1.5839. Min Act: -0.0001
Data Index: 479750 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8680. Min Range: -2.8680
Max Act: 1.6633. Min Act: -0.0001
Data Index: 1128053 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19