Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.8858. Min Act: -0.0001
Data Index: 1095414 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.8250. Min Act: -0.0001
Data Index: 25846 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.7101. Min Act: -0.0001
Data Index: 191582 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.7882. Min Act: -0.0001
Data Index: 395086 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.7322. Min Act: -0.0001
Data Index: 413612 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.7677. Min Act: -0.0001
Data Index: 724514 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.6807. Min Act: -0.0001
Data Index: 335304 (C4 (Web Text))
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.7109. Min Act: -0.0001
Data Index: 627097 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.6422. Min Act: -0.0001
Data Index: 609626 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.6691. Min Act: -0.0001
Data Index: 1220099 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.6170. Min Act: -0.0001
Data Index: 1180737 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.6010. Min Act: -0.0001
Data Index: 347006 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.6159. Min Act: -0.0001
Data Index: 497944 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.6318. Min Act: -0.0001
Data Index: 724867 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.6271. Min Act: -0.0001
Data Index: 376830 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.6275. Min Act: -0.0001
Data Index: 796411 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.6024. Min Act: -0.0001
Data Index: 1349377 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.6034. Min Act: -0.0001
Data Index: 977543 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.5921. Min Act: -0.0001
Data Index: 108809 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8858. Min Range: -0.8858
Max Act: 0.5829. Min Act: -0.0001
Data Index: 14560 (C4 (Web Text))
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19