Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3231 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.7913. Min Range: -2.7913
Max Act: 2.7913. Min Act: -0.0001
Data Index: 246145 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7913. Min Range: -2.7913
Max Act: 2.3661. Min Act: -0.0001
Data Index: 660393 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7913. Min Range: -2.7913
Max Act: 2.3921. Min Act: -0.0001
Data Index: 1012730 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7913. Min Range: -2.7913
Max Act: 2.0890. Min Act: -0.0000
Data Index: 507180 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7913. Min Range: -2.7913
Max Act: 2.0470. Min Act: -0.0001
Data Index: 277935 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7913. Min Range: -2.7913
Max Act: 1.8903. Min Act: -0.0001
Data Index: 538678 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7913. Min Range: -2.7913
Max Act: 1.8201. Min Act: -0.0000
Data Index: 1051966 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7913. Min Range: -2.7913
Max Act: 1.7330. Min Act: -0.0001
Data Index: 1051198 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7913. Min Range: -2.7913
Max Act: 1.6740. Min Act: -0.0001
Data Index: 995145 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7913. Min Range: -2.7913
Max Act: 1.6894. Min Act: -0.0000
Data Index: 459016 (C4 (Web Text))
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7913. Min Range: -2.7913
Max Act: 1.5815. Min Act: -0.0001
Data Index: 1017184 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7913. Min Range: -2.7913
Max Act: 1.6036. Min Act: -0.0001
Data Index: 286604 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7913. Min Range: -2.7913
Max Act: 1.6048. Min Act: -0.0001
Data Index: 1085346 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7913. Min Range: -2.7913
Max Act: 1.5457. Min Act: -0.0001
Data Index: 352762 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7913. Min Range: -2.7913
Max Act: 1.5429. Min Act: -0.0001
Data Index: 26501 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7913. Min Range: -2.7913
Max Act: 1.5137. Min Act: -0.0001
Data Index: 372244 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7913. Min Range: -2.7913
Max Act: 1.4070. Min Act: -0.0001
Data Index: 641021 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7913. Min Range: -2.7913
Max Act: 1.3556. Min Act: -0.0001
Data Index: 1105891 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7913. Min Range: -2.7913
Max Act: 1.3506. Min Act: -0.0001
Data Index: 239407 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7913. Min Range: -2.7913
Max Act: 1.2707. Min Act: -0.0001
Data Index: 83545 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19