Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2900 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.4721. Min Range: -2.4721
Max Act: 2.4721. Min Act: -0.0001
Data Index: 1035885 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4721. Min Range: -2.4721
Max Act: 2.2937. Min Act: -0.0001
Data Index: 189399 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4721. Min Range: -2.4721
Max Act: 2.2424. Min Act: -0.0000
Data Index: 1509319 (Python Code)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4721. Min Range: -2.4721
Max Act: 2.2925. Min Act: -0.0001
Data Index: 873267 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4721. Min Range: -2.4721
Max Act: 2.1103. Min Act: -0.0000
Data Index: 563474 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4721. Min Range: -2.4721
Max Act: 2.0079. Min Act: -0.0000
Data Index: 1580907 (Python Code)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4721. Min Range: -2.4721
Max Act: 1.9153. Min Act: -0.0000
Data Index: 1024607 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4721. Min Range: -2.4721
Max Act: 1.7318. Min Act: -0.0000
Data Index: 920704 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4721. Min Range: -2.4721
Max Act: 1.8976. Min Act: -0.0001
Data Index: 202803 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4721. Min Range: -2.4721
Max Act: 1.8705. Min Act: -0.0001
Data Index: 1285625 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4721. Min Range: -2.4721
Max Act: 1.7110. Min Act: -0.0000
Data Index: 802768 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4721. Min Range: -2.4721
Max Act: 1.6644. Min Act: -0.0001
Data Index: 1449119 (Python Code)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4721. Min Range: -2.4721
Max Act: 1.6541. Min Act: -0.0001
Data Index: 727216 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4721. Min Range: -2.4721
Max Act: 1.5456. Min Act: -0.0001
Data Index: 1624373 (Python Code)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4721. Min Range: -2.4721
Max Act: 1.7308. Min Act: -0.0001
Data Index: 932328 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4721. Min Range: -2.4721
Max Act: 1.6709. Min Act: -0.0001
Data Index: 1367307 (Python Code)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4721. Min Range: -2.4721
Max Act: 1.6377. Min Act: -0.0000
Data Index: 1587870 (Python Code)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4721. Min Range: -2.4721
Max Act: 1.7280. Min Act: -0.0001
Data Index: 183568 (C4 (Web Text))
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4721. Min Range: -2.4721
Max Act: 1.5422. Min Act: -0.0001
Data Index: 347193 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4721. Min Range: -2.4721
Max Act: 1.4088. Min Act: -0.0000
Data Index: 1349544 (C4 (Web Text))
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19