Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5262 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.7852. Min Range: -1.7852
Max Act: 1.6974. Min Act: -0.0001
Data Index: 986430 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7852. Min Range: -1.7852
Max Act: 1.6474. Min Act: -0.0001
Data Index: 470168 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7852. Min Range: -1.7852
Max Act: 1.6476. Min Act: -0.0001
Data Index: 50624 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7852. Min Range: -1.7852
Max Act: 1.6401. Min Act: -0.0001
Data Index: 257110 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7852. Min Range: -1.7852
Max Act: 1.6154. Min Act: -0.0001
Data Index: 968626 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7852. Min Range: -1.7852
Max Act: 1.6075. Min Act: -0.0001
Data Index: 1085901 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7852. Min Range: -1.7852
Max Act: 1.7852. Min Act: -0.0001
Data Index: 122825 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7852. Min Range: -1.7852
Max Act: 1.4099. Min Act: -0.0001
Data Index: 30727 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7852. Min Range: -1.7852
Max Act: 1.6350. Min Act: -0.0001
Data Index: 241527 (C4 (Web Text))
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7852. Min Range: -1.7852
Max Act: 1.4432. Min Act: -0.0001
Data Index: 402208 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7852. Min Range: -1.7852
Max Act: 1.4682. Min Act: -0.0001
Data Index: 526004 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7852. Min Range: -1.7852
Max Act: 1.4222. Min Act: -0.0001
Data Index: 240669 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7852. Min Range: -1.7852
Max Act: 1.4795. Min Act: -0.0001
Data Index: 965538 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7852. Min Range: -1.7852
Max Act: 1.4560. Min Act: -0.0001
Data Index: 337651 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7852. Min Range: -1.7852
Max Act: 1.3695. Min Act: -0.0001
Data Index: 1148755 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7852. Min Range: -1.7852
Max Act: 1.4247. Min Act: -0.0001
Data Index: 189290 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7852. Min Range: -1.7852
Max Act: 1.3635. Min Act: -0.0001
Data Index: 18550 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7852. Min Range: -1.7852
Max Act: 1.4290. Min Act: -0.0001
Data Index: 1118081 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7852. Min Range: -1.7852
Max Act: 1.3121. Min Act: -0.0001
Data Index: 1137939 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7852. Min Range: -1.7852
Max Act: 1.3353. Min Act: -0.0001
Data Index: 1039512 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19