Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2324 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 3.3893. Min Range: -3.3893
Max Act: 3.3893. Min Act: -0.0001
Data Index: 614522 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3893. Min Range: -3.3893
Max Act: 2.7992. Min Act: -0.0001
Data Index: 850053 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3893. Min Range: -3.3893
Max Act: 2.7533. Min Act: -0.0001
Data Index: 413524 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3893. Min Range: -3.3893
Max Act: 2.7001. Min Act: -0.0001
Data Index: 840462 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3893. Min Range: -3.3893
Max Act: 2.5733. Min Act: -0.0001
Data Index: 718532 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3893. Min Range: -3.3893
Max Act: 2.5687. Min Act: -0.0001
Data Index: 558608 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3893. Min Range: -3.3893
Max Act: 2.6388. Min Act: -0.0001
Data Index: 1172787 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3893. Min Range: -3.3893
Max Act: 2.5035. Min Act: -0.0001
Data Index: 678170 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3893. Min Range: -3.3893
Max Act: 2.3606. Min Act: -0.0001
Data Index: 982105 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3893. Min Range: -3.3893
Max Act: 2.7001. Min Act: -0.0001
Data Index: 869098 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3893. Min Range: -3.3893
Max Act: 2.5492. Min Act: -0.0001
Data Index: 989781 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3893. Min Range: -3.3893
Max Act: 2.5298. Min Act: -0.0001
Data Index: 268908 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3893. Min Range: -3.3893
Max Act: 2.2452. Min Act: -0.0001
Data Index: 1354201 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3893. Min Range: -3.3893
Max Act: 2.6399. Min Act: -0.0001
Data Index: 778835 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3893. Min Range: -3.3893
Max Act: 2.5259. Min Act: -0.0001
Data Index: 940670 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3893. Min Range: -3.3893
Max Act: 2.3511. Min Act: -0.0001
Data Index: 1288973 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3893. Min Range: -3.3893
Max Act: 2.1357. Min Act: -0.0001
Data Index: 1338590 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3893. Min Range: -3.3893
Max Act: 2.4275. Min Act: -0.0001
Data Index: 823885 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3893. Min Range: -3.3893
Max Act: 2.5846. Min Act: -0.0001
Data Index: 982845 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3893. Min Range: -3.3893
Max Act: 2.4270. Min Act: -0.0001
Data Index: 184803 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19