Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1573 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.9888. Min Range: -2.9888
Max Act: 2.7937. Min Act: -0.0001
Data Index: 1206880 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9888. Min Range: -2.9888
Max Act: 2.7357. Min Act: -0.0001
Data Index: 1059610 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9888. Min Range: -2.9888
Max Act: 2.9888. Min Act: -0.0001
Data Index: 790781 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9888. Min Range: -2.9888
Max Act: 2.5884. Min Act: -0.0001
Data Index: 1005656 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9888. Min Range: -2.9888
Max Act: 2.6910. Min Act: -0.0001
Data Index: 1229304 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9888. Min Range: -2.9888
Max Act: 2.6882. Min Act: -0.0001
Data Index: 254926 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9888. Min Range: -2.9888
Max Act: 2.5178. Min Act: -0.0001
Data Index: 926276 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9888. Min Range: -2.9888
Max Act: 2.3913. Min Act: -0.0001
Data Index: 683623 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9888. Min Range: -2.9888
Max Act: 2.4940. Min Act: -0.0001
Data Index: 726778 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9888. Min Range: -2.9888
Max Act: 2.6412. Min Act: -0.0001
Data Index: 168211 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9888. Min Range: -2.9888
Max Act: 2.6150. Min Act: -0.0001
Data Index: 590420 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9888. Min Range: -2.9888
Max Act: 2.5900. Min Act: -0.0001
Data Index: 1246152 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9888. Min Range: -2.9888
Max Act: 2.5812. Min Act: -0.0001
Data Index: 1219660 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9888. Min Range: -2.9888
Max Act: 2.4489. Min Act: -0.0001
Data Index: 60213 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9888. Min Range: -2.9888
Max Act: 2.5524. Min Act: -0.0001
Data Index: 286669 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9888. Min Range: -2.9888
Max Act: 2.6840. Min Act: -0.0001
Data Index: 599462 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9888. Min Range: -2.9888
Max Act: 2.5508. Min Act: -0.0001
Data Index: 537228 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9888. Min Range: -2.9888
Max Act: 2.5367. Min Act: -0.0001
Data Index: 1261270 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9888. Min Range: -2.9888
Max Act: 2.4994. Min Act: -0.0001
Data Index: 1259083 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9888. Min Range: -2.9888
Max Act: 2.5045. Min Act: -0.0001
Data Index: 24572 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19