Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4201 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.8902. Min Range: -1.8902
Max Act: 1.8902. Min Act: -0.0001
Data Index: 1345351 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8902. Min Range: -1.8902
Max Act: 1.5242. Min Act: -0.0001
Data Index: 422352 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8902. Min Range: -1.8902
Max Act: 1.5580. Min Act: -0.0001
Data Index: 731306 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8902. Min Range: -1.8902
Max Act: 1.3658. Min Act: -0.0001
Data Index: 202083 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8902. Min Range: -1.8902
Max Act: 1.3305. Min Act: -0.0001
Data Index: 748982 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8902. Min Range: -1.8902
Max Act: 1.2887. Min Act: -0.0001
Data Index: 52141 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8902. Min Range: -1.8902
Max Act: 1.2930. Min Act: -0.0001
Data Index: 1212932 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8902. Min Range: -1.8902
Max Act: 1.1964. Min Act: -0.0001
Data Index: 564484 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8902. Min Range: -1.8902
Max Act: 1.2635. Min Act: -0.0001
Data Index: 1151440 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8902. Min Range: -1.8902
Max Act: 1.0698. Min Act: -0.0001
Data Index: 1120261 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8902. Min Range: -1.8902
Max Act: 1.1724. Min Act: -0.0001
Data Index: 1148969 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8902. Min Range: -1.8902
Max Act: 1.1025. Min Act: -0.0001
Data Index: 563145 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8902. Min Range: -1.8902
Max Act: 1.1228. Min Act: -0.0001
Data Index: 86060 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8902. Min Range: -1.8902
Max Act: 1.1224. Min Act: -0.0001
Data Index: 1106936 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8902. Min Range: -1.8902
Max Act: 1.1158. Min Act: -0.0001
Data Index: 920198 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8902. Min Range: -1.8902
Max Act: 1.1023. Min Act: -0.0001
Data Index: 1245928 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8902. Min Range: -1.8902
Max Act: 0.9718. Min Act: -0.0001
Data Index: 1313423 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8902. Min Range: -1.8902
Max Act: 0.9921. Min Act: -0.0001
Data Index: 1350841 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8902. Min Range: -1.8902
Max Act: 0.8298. Min Act: -0.0001
Data Index: 84278 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8902. Min Range: -1.8902
Max Act: 1.0022. Min Act: -0.0001
Data Index: 387486 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19