Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1543 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.3508. Min Range: -1.3508
Max Act: 1.3508. Min Act: -0.0001
Data Index: 153590 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3508. Min Range: -1.3508
Max Act: 1.1349. Min Act: -0.0001
Data Index: 220971 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3508. Min Range: -1.3508
Max Act: 1.0937. Min Act: -0.0001
Data Index: 652170 (C4 (Web Text))
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3508. Min Range: -1.3508
Max Act: 1.0707. Min Act: -0.0001
Data Index: 670169 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3508. Min Range: -1.3508
Max Act: 1.0078. Min Act: -0.0001
Data Index: 880524 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3508. Min Range: -1.3508
Max Act: 1.0357. Min Act: -0.0001
Data Index: 683461 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3508. Min Range: -1.3508
Max Act: 0.8606. Min Act: -0.0001
Data Index: 262688 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3508. Min Range: -1.3508
Max Act: 1.0110. Min Act: -0.0001
Data Index: 464434 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3508. Min Range: -1.3508
Max Act: 0.9322. Min Act: -0.0001
Data Index: 813348 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3508. Min Range: -1.3508
Max Act: 0.9206. Min Act: -0.0001
Data Index: 60955 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3508. Min Range: -1.3508
Max Act: 0.9723. Min Act: -0.0001
Data Index: 816436 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3508. Min Range: -1.3508
Max Act: 0.8997. Min Act: -0.0001
Data Index: 176342 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3508. Min Range: -1.3508
Max Act: 0.8542. Min Act: -0.0001
Data Index: 442213 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3508. Min Range: -1.3508
Max Act: 0.7752. Min Act: -0.0001
Data Index: 466651 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3508. Min Range: -1.3508
Max Act: 0.8723. Min Act: -0.0001
Data Index: 985029 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3508. Min Range: -1.3508
Max Act: 0.8707. Min Act: -0.0001
Data Index: 667955 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3508. Min Range: -1.3508
Max Act: 0.8650. Min Act: -0.0001
Data Index: 434540 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3508. Min Range: -1.3508
Max Act: 0.8103. Min Act: -0.0001
Data Index: 804280 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3508. Min Range: -1.3508
Max Act: 0.8267. Min Act: -0.0001
Data Index: 1100564 (C4 (Web Text))
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3508. Min Range: -1.3508
Max Act: 0.7151. Min Act: -0.0001
Data Index: 484202 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19