Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3941 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.1552. Min Range: -3.1552
Max Act: 3.0672. Min Act: -0.0001
Data Index: 872025 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1552. Min Range: -3.1552
Max Act: 3.1552. Min Act: -0.0001
Data Index: 698396 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1552. Min Range: -3.1552
Max Act: 2.8137. Min Act: -0.0001
Data Index: 234485 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1552. Min Range: -3.1552
Max Act: 2.5914. Min Act: -0.0001
Data Index: 724087 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1552. Min Range: -3.1552
Max Act: 2.8225. Min Act: -0.0001
Data Index: 510473 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1552. Min Range: -3.1552
Max Act: 2.6253. Min Act: -0.0001
Data Index: 1272136 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1552. Min Range: -3.1552
Max Act: 2.6114. Min Act: -0.0001
Data Index: 658362 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1552. Min Range: -3.1552
Max Act: 2.6885. Min Act: -0.0001
Data Index: 561172 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1552. Min Range: -3.1552
Max Act: 2.5595. Min Act: -0.0001
Data Index: 742096 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1552. Min Range: -3.1552
Max Act: 2.5181. Min Act: -0.0001
Data Index: 1237425 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1552. Min Range: -3.1552
Max Act: 2.5197. Min Act: -0.0001
Data Index: 591625 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1552. Min Range: -3.1552
Max Act: 2.6486. Min Act: -0.0001
Data Index: 301420 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1552. Min Range: -3.1552
Max Act: 2.4092. Min Act: -0.0001
Data Index: 757090 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1552. Min Range: -3.1552
Max Act: 2.5006. Min Act: -0.0001
Data Index: 258601 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1552. Min Range: -3.1552
Max Act: 2.3862. Min Act: -0.0001
Data Index: 140851 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1552. Min Range: -3.1552
Max Act: 2.4664. Min Act: -0.0001
Data Index: 124623 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1552. Min Range: -3.1552
Max Act: 2.1860. Min Act: -0.0001
Data Index: 1245457 (C4 (Web Text))
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1552. Min Range: -3.1552
Max Act: 2.2260. Min Act: -0.0001
Data Index: 330868 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1552. Min Range: -3.1552
Max Act: 2.2761. Min Act: -0.0001
Data Index: 986687 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1552. Min Range: -3.1552
Max Act: 2.1857. Min Act: -0.0001
Data Index: 1575859 (Python Code)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19