Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1317 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.5037. Min Range: -2.5037
Max Act: 2.5036. Min Act: -0.0001
Data Index: 809379 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5037. Min Range: -2.5037
Max Act: 2.5037. Min Act: -0.0001
Data Index: 5993 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5037. Min Range: -2.5037
Max Act: 2.2540. Min Act: -0.0001
Data Index: 171898 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5037. Min Range: -2.5037
Max Act: 2.2703. Min Act: -0.0001
Data Index: 620454 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5037. Min Range: -2.5037
Max Act: 2.1720. Min Act: -0.0001
Data Index: 446045 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5037. Min Range: -2.5037
Max Act: 2.2110. Min Act: -0.0001
Data Index: 532114 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5037. Min Range: -2.5037
Max Act: 2.1026. Min Act: -0.0001
Data Index: 462550 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5037. Min Range: -2.5037
Max Act: 2.1693. Min Act: -0.0001
Data Index: 56740 (C4 (Web Text))
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5037. Min Range: -2.5037
Max Act: 2.1343. Min Act: -0.0001
Data Index: 1269096 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5037. Min Range: -2.5037
Max Act: 2.1330. Min Act: -0.0001
Data Index: 365952 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5037. Min Range: -2.5037
Max Act: 2.1828. Min Act: -0.0001
Data Index: 440293 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5037. Min Range: -2.5037
Max Act: 2.3583. Min Act: -0.0001
Data Index: 983377 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5037. Min Range: -2.5037
Max Act: 2.1042. Min Act: -0.0001
Data Index: 746417 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5037. Min Range: -2.5037
Max Act: 2.0611. Min Act: -0.0001
Data Index: 313069 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5037. Min Range: -2.5037
Max Act: 2.1846. Min Act: -0.0001
Data Index: 1095413 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5037. Min Range: -2.5037
Max Act: 2.2280. Min Act: -0.0001
Data Index: 672084 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5037. Min Range: -2.5037
Max Act: 1.9500. Min Act: -0.0001
Data Index: 396897 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5037. Min Range: -2.5037
Max Act: 2.1731. Min Act: -0.0001
Data Index: 577917 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5037. Min Range: -2.5037
Max Act: 2.0572. Min Act: -0.0001
Data Index: 700975 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5037. Min Range: -2.5037
Max Act: 2.0461. Min Act: -0.0001
Data Index: 540401 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19