Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3031 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.8371. Min Range: -2.8371
Max Act: 2.8371. Min Act: -0.0001
Data Index: 350103 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8371. Min Range: -2.8371
Max Act: 2.5559. Min Act: -0.0001
Data Index: 1310066 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8371. Min Range: -2.8371
Max Act: 2.4062. Min Act: -0.0001
Data Index: 767347 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8371. Min Range: -2.8371
Max Act: 2.4473. Min Act: -0.0000
Data Index: 351204 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8371. Min Range: -2.8371
Max Act: 2.4300. Min Act: -0.0001
Data Index: 1352527 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8371. Min Range: -2.8371
Max Act: 2.3008. Min Act: -0.0001
Data Index: 625089 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8371. Min Range: -2.8371
Max Act: 2.4853. Min Act: -0.0000
Data Index: 604130 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8371. Min Range: -2.8371
Max Act: 2.2090. Min Act: -0.0001
Data Index: 426251 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8371. Min Range: -2.8371
Max Act: 2.1579. Min Act: -0.0001
Data Index: 1043807 (C4 (Web Text))
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8371. Min Range: -2.8371
Max Act: 2.2473. Min Act: -0.0000
Data Index: 445334 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8371. Min Range: -2.8371
Max Act: 2.4790. Min Act: -0.0001
Data Index: 134691 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8371. Min Range: -2.8371
Max Act: 2.3285. Min Act: -0.0001
Data Index: 631452 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8371. Min Range: -2.8371
Max Act: 2.1035. Min Act: -0.0000
Data Index: 302459 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8371. Min Range: -2.8371
Max Act: 2.3124. Min Act: -0.0001
Data Index: 1088314 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8371. Min Range: -2.8371
Max Act: 2.1987. Min Act: -0.0001
Data Index: 1324797 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8371. Min Range: -2.8371
Max Act: 2.0523. Min Act: -0.0000
Data Index: 53583 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8371. Min Range: -2.8371
Max Act: 2.0688. Min Act: -0.0000
Data Index: 732809 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8371. Min Range: -2.8371
Max Act: 2.2294. Min Act: -0.0001
Data Index: 997447 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8371. Min Range: -2.8371
Max Act: 1.9925. Min Act: -0.0000
Data Index: 410287 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8371. Min Range: -2.8371
Max Act: 2.2050. Min Act: -0.0000
Data Index: 773875 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19