Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 433 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.1508. Min Range: -2.1508
Max Act: 2.0154. Min Act: -0.0001
Data Index: 1281071 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1508. Min Range: -2.1508
Max Act: 2.0705. Min Act: -0.0001
Data Index: 1065533 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1508. Min Range: -2.1508
Max Act: 2.0683. Min Act: -0.0001
Data Index: 1325481 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1508. Min Range: -2.1508
Max Act: 2.0678. Min Act: -0.0001
Data Index: 1155229 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1508. Min Range: -2.1508
Max Act: 1.9440. Min Act: -0.0001
Data Index: 781412 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1508. Min Range: -2.1508
Max Act: 2.0660. Min Act: -0.0001
Data Index: 1136786 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1508. Min Range: -2.1508
Max Act: 2.0499. Min Act: -0.0001
Data Index: 1282688 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1508. Min Range: -2.1508
Max Act: 2.0351. Min Act: -0.0001
Data Index: 1272850 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1508. Min Range: -2.1508
Max Act: 1.9399. Min Act: -0.0001
Data Index: 702570 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1508. Min Range: -2.1508
Max Act: 2.0572. Min Act: -0.0001
Data Index: 44557 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1508. Min Range: -2.1508
Max Act: 1.9309. Min Act: -0.0001
Data Index: 936992 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1508. Min Range: -2.1508
Max Act: 1.9390. Min Act: -0.0001
Data Index: 983213 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1508. Min Range: -2.1508
Max Act: 2.1508. Min Act: -0.0001
Data Index: 455254 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1508. Min Range: -2.1508
Max Act: 2.0361. Min Act: -0.0001
Data Index: 352768 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1508. Min Range: -2.1508
Max Act: 1.9190. Min Act: -0.0001
Data Index: 454532 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1508. Min Range: -2.1508
Max Act: 2.0203. Min Act: -0.0001
Data Index: 213630 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1508. Min Range: -2.1508
Max Act: 1.9957. Min Act: -0.0001
Data Index: 521046 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1508. Min Range: -2.1508
Max Act: 1.8864. Min Act: -0.0001
Data Index: 837652 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1508. Min Range: -2.1508
Max Act: 1.9061. Min Act: -0.0001
Data Index: 1327288 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1508. Min Range: -2.1508
Max Act: 1.9897. Min Act: -0.0001
Data Index: 802193 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #19