Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3080 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.7422. Min Range: -3.7422
Max Act: 3.7422. Min Act: -0.0001
Data Index: 585884 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7422. Min Range: -3.7422
Max Act: 3.4360. Min Act: -0.0001
Data Index: 670511 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7422. Min Range: -3.7422
Max Act: 3.3091. Min Act: -0.0001
Data Index: 17919 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7422. Min Range: -3.7422
Max Act: 3.0037. Min Act: -0.0001
Data Index: 622712 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7422. Min Range: -3.7422
Max Act: 2.9766. Min Act: -0.0001
Data Index: 623955 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7422. Min Range: -3.7422
Max Act: 2.9732. Min Act: -0.0001
Data Index: 786574 (C4 (Web Text))
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7422. Min Range: -3.7422
Max Act: 2.7147. Min Act: -0.0001
Data Index: 415232 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7422. Min Range: -3.7422
Max Act: 2.8172. Min Act: -0.0001
Data Index: 1128636 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7422. Min Range: -3.7422
Max Act: 2.8197. Min Act: -0.0001
Data Index: 1215477 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7422. Min Range: -3.7422
Max Act: 2.7318. Min Act: -0.0001
Data Index: 1157570 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7422. Min Range: -3.7422
Max Act: 2.6852. Min Act: -0.0000
Data Index: 1043181 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7422. Min Range: -3.7422
Max Act: 2.6782. Min Act: -0.0001
Data Index: 1202152 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7422. Min Range: -3.7422
Max Act: 2.6283. Min Act: -0.0001
Data Index: 745718 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7422. Min Range: -3.7422
Max Act: 2.8974. Min Act: -0.0001
Data Index: 386342 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7422. Min Range: -3.7422
Max Act: 2.6105. Min Act: -0.0001
Data Index: 249543 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7422. Min Range: -3.7422
Max Act: 2.4692. Min Act: -0.0001
Data Index: 784514 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7422. Min Range: -3.7422
Max Act: 2.6841. Min Act: -0.0001
Data Index: 217005 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7422. Min Range: -3.7422
Max Act: 2.5476. Min Act: -0.0001
Data Index: 362274 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7422. Min Range: -3.7422
Max Act: 2.3226. Min Act: -0.0001
Data Index: 334300 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7422. Min Range: -3.7422
Max Act: 2.4471. Min Act: -0.0001
Data Index: 886382 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19